Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Alekh Agarwal
@article{DBLP:journals/corr/abs-2401-01879,
author = {Ahmad Beirami and
Alekh Agarwal and
Jonathan Berant and
Alexander D'Amour and
Jacob Eisenstein and
Chirag Nagpal and
Ananda Theertha Suresh},
title = {Theoretical guarantees on the best-of-n alignment policy},
journal = {CoRR},
volume = {abs/2401.01879},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.01879},
doi = {10.48550/ARXIV.2401.01879},
eprinttype = {arXiv},
eprint = {2401.01879},
timestamp = {Tue, 23 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-01879.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-04056,
author = {Gokul Swamy and
Christoph Dann and
Rahul Kidambi and
Zhiwei Steven Wu and
Alekh Agarwal},
title = {A Minimaximalist Approach to Reinforcement Learning from Human Feedback},
journal = {CoRR},
volume = {abs/2401.04056},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.04056},
doi = {10.48550/ARXIV.2401.04056},
eprinttype = {arXiv},
eprint = {2401.04056},
timestamp = {Wed, 24 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-04056.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-07198,
author = {Kaiwen Wang and
Owen Oertell and
Alekh Agarwal and
Nathan Kallus and
Wen Sun},
title = {More Benefits of Being Distributional: Second-Order Bounds for Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2402.07198},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.07198},
doi = {10.48550/ARXIV.2402.07198},
eprinttype = {arXiv},
eprint = {2402.07198},
timestamp = {Fri, 16 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-07198.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-17235,
author = {Jincheng Mei and
Zixin Zhong and
Bo Dai and
Alekh Agarwal and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
title = {Stochastic Gradient Succeeds for Bandits},
journal = {CoRR},
volume = {abs/2402.17235},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.17235},
doi = {10.48550/ARXIV.2402.17235},
eprinttype = {arXiv},
eprint = {2402.17235},
timestamp = {Mon, 25 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-17235.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2403-19462,
author = {Teodor V. Marinov and
Alekh Agarwal and
Mircea Trofin},
title = {Offline Imitation Learning from Multiple Baselines with Applications
to Compiler Optimization},
journal = {CoRR},
volume = {abs/2403.19462},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2403.19462},
doi = {10.48550/ARXIV.2403.19462},
eprinttype = {arXiv},
eprint = {2403.19462},
timestamp = {Wed, 10 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2403-19462.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalJ023,
author = {Alekh Agarwal and
Yujia Jin and
Tong Zhang},
editor = {Gergely Neu and
Lorenzo Rosasco},
title = {{VOQL:} Towards Optimal Regret in Model-free {RL} with Nonlinear Function
Approximation},
booktitle = {The Thirty Sixth Annual Conference on Learning Theory, {COLT} 2023,
12-15 July 2023, Bangalore, India},
series = {Proceedings of Machine Learning Research},
volume = {195},
pages = {987--1063},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v195/agarwal23a.html},
timestamp = {Wed, 06 Sep 2023 17:49:05 +0200},
biburl = {https://dblp.org/rec/conf/colt/AgarwalJ023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/Agarwal00WWZ23,
author = {Alekh Agarwal and
Yuda Song and
Wen Sun and
Kaiwen Wang and
Mengdi Wang and
Xuezhou Zhang},
editor = {Gergely Neu and
Lorenzo Rosasco},
title = {Provable Benefits of Representational Transfer in Reinforcement Learning},
booktitle = {The Thirty Sixth Annual Conference on Learning Theory, {COLT} 2023,
12-15 July 2023, Bangalore, India},
series = {Proceedings of Machine Learning Research},
volume = {195},
pages = {2114--2187},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v195/agarwal23b.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/Agarwal00WWZ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/0002AD023,
author = {Jonathan Lee and
Alekh Agarwal and
Christoph Dann and
Tong Zhang},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Learning in POMDPs is Sample-Efficient with Hindsight Observability},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {18733--18773},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/lee23a.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/0002AD023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MeiZ0ASS23,
author = {Jincheng Mei and
Zixin Zhong and
Bo Dai and
Alekh Agarwal and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Stochastic Gradient Succeeds for Bandits},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {24325--24360},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/mei23a.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MeiZ0ASS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Mei0AGSS23,
author = {Jincheng Mei and
Bo Dai and
Alekh Agarwal and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Dale Schuurmans},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Ordering-based Conditions for Global Convergence of Policy Gradient
Methods},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/61c00c07e6d27285e4b952e96cc65666-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Mei0AGSS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-13857,
author = {Jonathan N. Lee and
Alekh Agarwal and
Christoph Dann and
Tong Zhang},
title = {Learning in POMDPs is Sample-Efficient with Hindsight Observability},
journal = {CoRR},
volume = {abs/2301.13857},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.13857},
doi = {10.48550/ARXIV.2301.13857},
eprinttype = {arXiv},
eprint = {2301.13857},
timestamp = {Wed, 08 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-13857.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-03784,
author = {Alekh Agarwal and
Claudio Gentile and
Teodor V. Marinov},
title = {Leveraging User-Triggered Supervision in Contextual Bandits},
journal = {CoRR},
volume = {abs/2302.03784},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.03784},
doi = {10.48550/ARXIV.2302.03784},
eprinttype = {arXiv},
eprint = {2302.03784},
timestamp = {Fri, 10 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-03784.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-10218,
author = {Alekh Agarwal and
H. Brendan McMahan and
Zheng Xu},
title = {An Empirical Evaluation of Federated Contextual Bandit Algorithms},
journal = {CoRR},
volume = {abs/2303.10218},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.10218},
doi = {10.48550/ARXIV.2303.10218},
eprinttype = {arXiv},
eprint = {2303.10218},
timestamp = {Wed, 22 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-10218.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-17040,
author = {Jacob D. Abernethy and
Alekh Agarwal and
Teodor V. Marinov and
Manfred K. Warmuth},
title = {A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval
Tasks},
journal = {CoRR},
volume = {abs/2305.17040},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.17040},
doi = {10.48550/ARXIV.2305.17040},
eprinttype = {arXiv},
eprint = {2305.17040},
timestamp = {Wed, 07 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-17040.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-09497,
author = {Alexander Goldberg and
Ivan Stelmakh and
Kyunghyun Cho and
Alice H. Oh and
Alekh Agarwal and
Danielle Belgrave and
Nihar B. Shah},
title = {Peer Reviews of Peer Reviews: {A} Randomized Controlled Trial and
Other Experiments},
journal = {CoRR},
volume = {abs/2311.09497},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.09497},
doi = {10.48550/ARXIV.2311.09497},
eprinttype = {arXiv},
eprint = {2311.09497},
timestamp = {Tue, 21 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-09497.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-09612,
author = {Wang Zhu and
Alekh Agarwal and
Mandar Joshi and
Robin Jia and
Jesse Thomason and
Kristina Toutanova},
title = {Efficient End-to-End Visual Document Understanding with Rationale
Distillation},
journal = {CoRR},
volume = {abs/2311.09612},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.09612},
doi = {10.48550/ARXIV.2311.09612},
eprinttype = {arXiv},
eprint = {2311.09612},
timestamp = {Tue, 21 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-09612.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-09244,
author = {Jacob Eisenstein and
Chirag Nagpal and
Alekh Agarwal and
Ahmad Beirami and
Alex D'Amour and
Dj Dvijotham and
Adam Fisch and
Katherine A. Heller and
Stephen Pfohl and
Deepak Ramachandran and
Peter Shaw and
Jonathan Berant},
title = {Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate
Reward Hacking},
journal = {CoRR},
volume = {abs/2312.09244},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.09244},
doi = {10.48550/ARXIV.2312.09244},
eprinttype = {arXiv},
eprint = {2312.09244},
timestamp = {Tue, 09 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-09244.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalZ22,
author = {Alekh Agarwal and
Tong Zhang},
editor = {Po{-}Ling Loh and
Maxim Raginsky},
title = {Minimax Regret Optimization for Robust Machine Learning under Distribution
Shift},
booktitle = {Conference on Learning Theory, 2-5 July 2022, London, {UK}},
series = {Proceedings of Machine Learning Research},
volume = {178},
pages = {2704--2729},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v178/agarwal22b.html},
timestamp = {Wed, 08 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/AgarwalZ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalZ22a,
author = {Alekh Agarwal and
Tong Zhang},
editor = {Po{-}Ling Loh and
Maxim Raginsky},
title = {Non-Linear Reinforcement Learning in Large Action Spaces: Structural
Conditions and Sample-efficiency of Posterior Sampling},
booktitle = {Conference on Learning Theory, 2-5 July 2022, London, {UK}},
series = {Proceedings of Machine Learning Research},
volume = {178},
pages = {2776--2814},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v178/agarwal22c.html},
timestamp = {Wed, 08 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/AgarwalZ22a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/EfroniMKA022,
author = {Yonathan Efroni and
Dipendra Misra and
Akshay Krishnamurthy and
Alekh Agarwal and
John Langford},
title = {Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics},
booktitle = {The Tenth International Conference on Learning Representations, {ICLR}
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=RQLLzMCefQu},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/EfroniMKA022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ChengX0A22,
author = {Ching{-}An Cheng and
Tengyang Xie and
Nan Jiang and
Alekh Agarwal},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {Adversarially Trained Actor Critic for Offline Reinforcement Learning},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {3852--3878},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/cheng22b.html},
timestamp = {Tue, 12 Jul 2022 17:36:52 +0200},
biburl = {https://dblp.org/rec/conf/icml/ChengX0A22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhangSUWAS22,
author = {Xuezhou Zhang and
Yuda Song and
Masatoshi Uehara and
Mengdi Wang and
Alekh Agarwal and
Wen Sun},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {Efficient Reinforcement Learning in Block MDPs: {A} Model-free Representation
Learning approach},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {26517--26547},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/zhang22aa.html},
timestamp = {Wed, 10 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZhangSUWAS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Agarwal022,
author = {Alekh Agarwal and
Tong Zhang},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Model-based {RL} with Optimistic Posterior Sampling: Structural Conditions
and Sample Complexity},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/e536e43b01a4387a2282c2b04103c802-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Agarwal022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Chen0K0A22,
author = {Jinglin Chen and
Aditya Modi and
Akshay Krishnamurthy and
Nan Jiang and
Alekh Agarwal},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {On the Statistical Efficiency of Reward-Free Exploration in Non-Linear
{RL}},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/8433bb4f7477bf8202614ce1ae8b1169-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Chen0K0A22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-00063,
author = {Xuezhou Zhang and
Yuda Song and
Masatoshi Uehara and
Mengdi Wang and
Alekh Agarwal and
Wen Sun},
title = {Efficient Reinforcement Learning in Block MDPs: {A} Model-free Representation
Learning Approach},
journal = {CoRR},
volume = {abs/2202.00063},
year = {2022},
url = {https://arxiv.org/abs/2202.00063},
eprinttype = {arXiv},
eprint = {2202.00063},
timestamp = {Wed, 10 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-00063.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-02446,
author = {Ching{-}An Cheng and
Tengyang Xie and
Nan Jiang and
Alekh Agarwal},
title = {Adversarially Trained Actor Critic for Offline Reinforcement Learning},
journal = {CoRR},
volume = {abs/2202.02446},
year = {2022},
url = {https://arxiv.org/abs/2202.02446},
eprinttype = {arXiv},
eprint = {2202.02446},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-02446.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-05436,
author = {Alekh Agarwal and
Tong Zhang},
title = {Minimax Regret Optimization for Robust Machine Learning under Distribution
Shift},
journal = {CoRR},
volume = {abs/2202.05436},
year = {2022},
url = {https://arxiv.org/abs/2202.05436},
eprinttype = {arXiv},
eprint = {2202.05436},
timestamp = {Wed, 08 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-05436.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-08248,
author = {Alekh Agarwal and
Tong Zhang},
title = {Non-Linear Reinforcement Learning in Large Action Spaces: Structural
Conditions and Sample-efficiency of Posterior Sampling},
journal = {CoRR},
volume = {abs/2203.08248},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.08248},
doi = {10.48550/ARXIV.2203.08248},
eprinttype = {arXiv},
eprint = {2203.08248},
timestamp = {Wed, 08 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-08248.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-14571,
author = {Alekh Agarwal and
Yuda Song and
Wen Sun and
Kaiwen Wang and
Mengdi Wang and
Xuezhou Zhang},
title = {Provable Benefits of Representational Transfer in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2205.14571},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.14571},
doi = {10.48550/ARXIV.2205.14571},
eprinttype = {arXiv},
eprint = {2205.14571},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-14571.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-07659,
author = {Alekh Agarwal and
Tong Zhang},
title = {Model-based {RL} with Optimistic Posterior Sampling: Structural Conditions
and Sample Complexity},
journal = {CoRR},
volume = {abs/2206.07659},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.07659},
doi = {10.48550/ARXIV.2206.07659},
eprinttype = {arXiv},
eprint = {2206.07659},
timestamp = {Wed, 08 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-07659.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-10770,
author = {Jinglin Chen and
Aditya Modi and
Akshay Krishnamurthy and
Nan Jiang and
Alekh Agarwal},
title = {On the Statistical Efficiency of Reward-Free Exploration in Non-Linear
{RL}},
journal = {CoRR},
volume = {abs/2206.10770},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.10770},
doi = {10.48550/ARXIV.2206.10770},
eprinttype = {arXiv},
eprint = {2206.10770},
timestamp = {Mon, 27 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-10770.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-06069,
author = {Alekh Agarwal and
Yujia Jin and
Tong Zhang},
title = {{VOQL:} Towards Optimal Regret in Model-free {RL} with Nonlinear Function
Approximation},
journal = {CoRR},
volume = {abs/2212.06069},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.06069},
doi = {10.48550/ARXIV.2212.06069},
eprinttype = {arXiv},
eprint = {2212.06069},
timestamp = {Wed, 08 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-06069.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/AgarwalKLM21,
author = {Alekh Agarwal and
Sham M. Kakade and
Jason D. Lee and
Gaurav Mahajan},
title = {On the Theory of Policy Gradient Methods: Optimality, Approximation,
and Distribution Shift},
journal = {J. Mach. Learn. Res.},
volume = {22},
pages = {98:1--98:76},
year = {2021},
url = {http://jmlr.org/papers/v22/19-736.html},
timestamp = {Mon, 31 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jmlr/AgarwalKLM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/BiettiAL21,
author = {Alberto Bietti and
Alekh Agarwal and
John Langford},
title = {A Contextual Bandit Bake-off},
journal = {J. Mach. Learn. Res.},
volume = {22},
pages = {133:1--133:49},
year = {2021},
url = {http://jmlr.org/papers/v22/18-863.html},
timestamp = {Mon, 31 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jmlr/BiettiAL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/PerdomoSAB21,
author = {Juan C. Perdomo and
Max Simchowitz and
Alekh Agarwal and
Peter L. Bartlett},
editor = {Mikhail Belkin and
Samory Kpotufe},
title = {Towards a Dimension-Free Understanding of Adaptive Linear Control},
booktitle = {Conference on Learning Theory, {COLT} 2021, 15-19 August 2021, Boulder,
Colorado, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {134},
pages = {3681--3770},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v134/perdomo21a.html},
timestamp = {Wed, 25 Aug 2021 17:11:16 +0200},
biburl = {https://dblp.org/rec/conf/colt/PerdomoSAB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/ZanetteCA21,
author = {Andrea Zanette and
Ching{-}An Cheng and
Alekh Agarwal},
editor = {Mikhail Belkin and
Samory Kpotufe},
title = {Cautiously Optimistic Policy Optimization and Exploration with Linear
Function Approximation},
booktitle = {Conference on Learning Theory, {COLT} 2021, 15-19 August 2021, Boulder,
Colorado, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {134},
pages = {4473--4525},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v134/zanette21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/ZanetteCA21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/FengYA021,
author = {Fei Feng and
Wotao Yin and
Alekh Agarwal and
Lin Yang},
editor = {Marina Meila and
Tong Zhang},
title = {Provably Correct Optimization and Exploration with Non-linear Policies},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {3263--3273},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/feng21e.html},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/FengYA021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/XieCJMA21,
author = {Tengyang Xie and
Ching{-}An Cheng and
Nan Jiang and
Paul Mineiro and
Alekh Agarwal},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Bellman-consistent Pessimism for Offline Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {6683--6694},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/34f98c7c5d7063181da890ea8d25265a-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/XieCJMA21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-07035,
author = {Aditya Modi and
Jinglin Chen and
Akshay Krishnamurthy and
Nan Jiang and
Alekh Agarwal},
title = {Model-free Representation Learning and Exploration in Low-rank MDPs},
journal = {CoRR},
volume = {abs/2102.07035},
year = {2021},
url = {https://arxiv.org/abs/2102.07035},
eprinttype = {arXiv},
eprint = {2102.07035},
timestamp = {Fri, 19 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-07035.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-10620,
author = {Juan C. Perdomo and
Max Simchowitz and
Alekh Agarwal and
Peter L. Bartlett},
title = {Towards a Dimension-Free Understanding of Adaptive Linear Control},
journal = {CoRR},
volume = {abs/2103.10620},
year = {2021},
url = {https://arxiv.org/abs/2103.10620},
eprinttype = {arXiv},
eprint = {2103.10620},
timestamp = {Wed, 24 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-10620.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-11559,
author = {Fei Feng and
Wotao Yin and
Alekh Agarwal and
Lin F. Yang},
title = {Provably Correct Optimization and Exploration with Non-linear Policies},
journal = {CoRR},
volume = {abs/2103.11559},
year = {2021},
url = {https://arxiv.org/abs/2103.11559},
eprinttype = {arXiv},
eprint = {2103.11559},
timestamp = {Wed, 24 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-11559.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-12923,
author = {Andrea Zanette and
Ching{-}An Cheng and
Alekh Agarwal},
title = {Cautiously Optimistic Policy Optimization and Exploration with Linear
Function Approximation},
journal = {CoRR},
volume = {abs/2103.12923},
year = {2021},
url = {https://arxiv.org/abs/2103.12923},
eprinttype = {arXiv},
eprint = {2103.12923},
timestamp = {Tue, 06 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-12923.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-06926,
author = {Tengyang Xie and
Ching{-}An Cheng and
Nan Jiang and
Paul Mineiro and
Alekh Agarwal},
title = {Bellman-consistent Pessimism for Offline Reinforcement Learning},
journal = {CoRR},
volume = {abs/2106.06926},
year = {2021},
url = {https://arxiv.org/abs/2106.06926},
eprinttype = {arXiv},
eprint = {2106.06926},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-06926.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-08847,
author = {Yonathan Efroni and
Dipendra Misra and
Akshay Krishnamurthy and
Alekh Agarwal and
John Langford},
title = {Provable {RL} with Exogenous Distractors via Multistep Inverse Dynamics},
journal = {CoRR},
volume = {abs/2110.08847},
year = {2021},
url = {https://arxiv.org/abs/2110.08847},
eprinttype = {arXiv},
eprint = {2110.08847},
timestamp = {Fri, 22 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-08847.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/0002DASNAH20,
author = {Aditya Modi and
Debadeepta Dey and
Alekh Agarwal and
Adith Swaminathan and
Besmira Nushi and
Sean Andrist and
Eric Horvitz},
title = {Metareasoning in Modular Software Systems: On-the-Fly Configuration
Using Reinforcement Learning with Rich Contextual Representations},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {5207--5215},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i04.5965},
doi = {10.1609/AAAI.V34I04.5965},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/0002DASNAH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalKLM20,
author = {Alekh Agarwal and
Sham M. Kakade and
Jason D. Lee and
Gaurav Mahajan},
editor = {Jacob D. Abernethy and
Shivani Agarwal},
title = {Optimality and Approximation with Policy Gradient Methods in Markov
Decision Processes},
booktitle = {Conference on Learning Theory, {COLT} 2020, 9-12 July 2020, Virtual
Event [Graz, Austria]},
series = {Proceedings of Machine Learning Research},
volume = {125},
pages = {64--66},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v125/agarwal20a.html},
timestamp = {Fri, 27 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/AgarwalKLM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalKY20,
author = {Alekh Agarwal and
Sham M. Kakade and
Lin F. Yang},
editor = {Jacob D. Abernethy and
Shivani Agarwal},
title = {Model-Based Reinforcement Learning with a Generative Model is Minimax
Optimal},
booktitle = {Conference on Learning Theory, {COLT} 2020, 9-12 July 2020, Virtual
Event [Graz, Austria]},
series = {Proceedings of Machine Learning Research},
volume = {125},
pages = {67--83},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v125/agarwal20b.html},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/AgarwalKY20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/WeiLA20,
author = {Chen{-}Yu Wei and
Haipeng Luo and
Alekh Agarwal},
editor = {Jacob D. Abernethy and
Shivani Agarwal},
title = {Taking a hint: How to leverage loss predictors in contextual bandits?},
booktitle = {Conference on Learning Theory, {COLT} 2020, 9-12 July 2020, Virtual
Event [Graz, Austria]},
series = {Proceedings of Machine Learning Research},
volume = {125},
pages = {3583--3634},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v125/wei20a.html},
timestamp = {Fri, 27 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/WeiLA20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/AshZK0A20,
author = {Jordan T. Ash and
Chicheng Zhang and
Akshay Krishnamurthy and
John Langford and
Alekh Agarwal},
title = {Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=ryghZJBKPS},
timestamp = {Thu, 07 May 2020 17:11:47 +0200},
biburl = {https://dblp.org/rec/conf/iclr/AshZK0A20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/0009SAB20,
author = {Yao Liu and
Adith Swaminathan and
Alekh Agarwal and
Emma Brunskill},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Provably Good Batch Off-Policy Reinforcement Learning Without Great
Exploration},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/0dc23b6a0e4abc39904388dd3ffadcd1-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/0009SAB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AgarwalHKS20,
author = {Alekh Agarwal and
Mikael Henaff and
Sham M. Kakade and
Wen Sun},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {{PC-PG:} Policy Cover Directed Exploration for Provable Policy Gradient
Learning},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/9b3a9fb4db30fc6594ec3990cbc09932-Abstract.html},
timestamp = {Thu, 17 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/AgarwalHKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AgarwalKKS20,
author = {Alekh Agarwal and
Sham M. Kakade and
Akshay Krishnamurthy and
Wen Sun},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {{FLAMBE:} Structural Complexity and Representation Learning of Low
Rank MDPs},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/e894d787e2fd6c133af47140aa156f00-Abstract.html},
timestamp = {Thu, 17 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/AgarwalKKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ChengKA20,
author = {Ching{-}An Cheng and
Andrey Kolobov and
Alekh Agarwal},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Policy Improvement via Imitation of Multiple Oracles},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/3c56fe2f24038c4d22b9eb0aca78f590-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ChengKA20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/TurchettaKS0A20,
author = {Matteo Turchetta and
Andrey Kolobov and
Shital Shah and
Andreas Krause and
Alekh Agarwal},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Safe Reinforcement Learning via Curriculum Induction},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/8df6a65941e4c9da40a4fb899de65c55-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/TurchettaKS0A20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-01922,
author = {Chen{-}Yu Wei and
Haipeng Luo and
Alekh Agarwal},
title = {Taking a hint: How to leverage loss predictors in contextual bandits?},
journal = {CoRR},
volume = {abs/2003.01922},
year = {2020},
url = {https://arxiv.org/abs/2003.01922},
eprinttype = {arXiv},
eprint = {2003.01922},
timestamp = {Tue, 10 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-01922.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-12880,
author = {Alekh Agarwal and
John Langford and
Chen{-}Yu Wei},
title = {Federated Residual Learning},
journal = {CoRR},
volume = {abs/2003.12880},
year = {2020},
url = {https://arxiv.org/abs/2003.12880},
eprinttype = {arXiv},
eprint = {2003.12880},
timestamp = {Wed, 01 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-12880.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-10810,
author = {Dilip Arumugam and
Debadeepta Dey and
Alekh Agarwal and
Asli Celikyilmaz and
Elnaz Nouri and
Bill Dolan},
title = {Reparameterized Variational Divergence Minimization for Stable Imitation},
journal = {CoRR},
volume = {abs/2006.10810},
year = {2020},
url = {https://arxiv.org/abs/2006.10810},
eprinttype = {arXiv},
eprint = {2006.10810},
timestamp = {Wed, 03 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-10810.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-10814,
author = {Alekh Agarwal and
Sham M. Kakade and
Akshay Krishnamurthy and
Wen Sun},
title = {{FLAMBE:} Structural Complexity and Representation Learning of Low
Rank MDPs},
journal = {CoRR},
volume = {abs/2006.10814},
year = {2020},
url = {https://arxiv.org/abs/2006.10814},
eprinttype = {arXiv},
eprint = {2006.10814},
timestamp = {Thu, 17 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-10814.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-12136,
author = {Matteo Turchetta and
Andrey Kolobov and
Shital Shah and
Andreas Krause and
Alekh Agarwal},
title = {Safe Reinforcement Learning via Curriculum Induction},
journal = {CoRR},
volume = {abs/2006.12136},
year = {2020},
url = {https://arxiv.org/abs/2006.12136},
eprinttype = {arXiv},
eprint = {2006.12136},
timestamp = {Tue, 23 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-12136.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-12999,
author = {Ziming Li and
Julia Kiseleva and
Alekh Agarwal and
Maarten de Rijke and
Ryen W. White},
title = {Optimizing Interactive Systems via Data-Driven Objectives},
journal = {CoRR},
volume = {abs/2006.12999},
year = {2020},
url = {https://arxiv.org/abs/2006.12999},
eprinttype = {arXiv},
eprint = {2006.12999},
timestamp = {Tue, 01 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-12999.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-00795,
author = {Ching{-}An Cheng and
Andrey Kolobov and
Alekh Agarwal},
title = {Policy Improvement from Multiple Experts},
journal = {CoRR},
volume = {abs/2007.00795},
year = {2020},
url = {https://arxiv.org/abs/2007.00795},
eprinttype = {arXiv},
eprint = {2007.00795},
timestamp = {Mon, 06 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-00795.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-08202,
author = {Yao Liu and
Adith Swaminathan and
Alekh Agarwal and
Emma Brunskill},
title = {Provably Good Batch Reinforcement Learning Without Great Exploration},
journal = {CoRR},
volume = {abs/2007.08202},
year = {2020},
url = {https://arxiv.org/abs/2007.08202},
eprinttype = {arXiv},
eprint = {2007.08202},
timestamp = {Wed, 22 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-08202.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-08459,
author = {Alekh Agarwal and
Mikael Henaff and
Sham M. Kakade and
Wen Sun},
title = {{PC-PG:} Policy Cover Directed Exploration for Provable Policy Gradient
Learning},
journal = {CoRR},
volume = {abs/2007.08459},
year = {2020},
url = {https://arxiv.org/abs/2007.08459},
eprinttype = {arXiv},
eprint = {2007.08459},
timestamp = {Thu, 17 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-08459.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/KrishnamurthyAH19,
author = {Akshay Krishnamurthy and
Alekh Agarwal and
Tzu{-}Kuo Huang and
Hal Daum{\'{e}} III and
John Langford},
title = {Active Learning for Cost-Sensitive Classification},
journal = {J. Mach. Learn. Res.},
volume = {20},
pages = {65:1--65:50},
year = {2019},
url = {http://jmlr.org/papers/v20/17-681.html},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/KrishnamurthyAH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/SunJKA019,
author = {Wen Sun and
Nan Jiang and
Akshay Krishnamurthy and
Alekh Agarwal and
John Langford},
editor = {Alina Beygelzimer and
Daniel Hsu},
title = {Model-based {RL} in Contextual Decision Processes: {PAC} bounds and
Exponential Improvements over Model-free Approaches},
booktitle = {Conference on Learning Theory, {COLT} 2019, 25-28 June 2019, Phoenix,
AZ, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {99},
pages = {2898--2933},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v99/sun19a.html},
timestamp = {Thu, 17 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/SunJKA019.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/GroverSKTAHE19,
author = {Aditya Grover and
Jiaming Song and
Ashish Kapoor and
Kenneth Tran and
Alekh Agarwal and
Eric Horvitz and
Stefano Ermon},
title = {Bias Correction of Learned Generative Models via Likelihood-free Importance
Weighting},
booktitle = {Deep Generative Models for Highly Structured Data, {ICLR} 2019 Workshop,
New Orleans, Louisiana, United States, May 6, 2019},
publisher = {OpenReview.net},
year = {2019},
url = {https://openreview.net/forum?id=SJe0ELLKuE},
timestamp = {Thu, 25 Jul 2019 16:26:32 +0200},
biburl = {https://dblp.org/rec/conf/iclr/GroverSKTAHE19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AgarwalDW19,
author = {Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
Zhiwei Steven Wu},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {Fair Regression: Quantitative Definitions and Reduction-Based Algorithms},
booktitle = {Proceedings of the 36th International Conference on Machine Learning,
{ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {97},
pages = {120--129},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/agarwal19d.html},
timestamp = {Tue, 11 Jun 2019 15:37:38 +0200},
biburl = {https://dblp.org/rec/conf/icml/AgarwalDW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/DuKJAD019,
author = {Simon S. Du and
Akshay Krishnamurthy and
Nan Jiang and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
John Langford},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {Provably efficient {RL} with Rich Observations via Latent State Decoding},
booktitle = {Proceedings of the 36th International Conference on Machine Learning,
{ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {97},
pages = {1665--1674},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/du19b.html},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/DuKJAD019.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhangAD0N19,
author = {Chicheng Zhang and
Alekh Agarwal and
Hal Daum{\'{e}} III and
John Langford and
Sahand Negahban},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {Warm-starting Contextual Bandits: Robustly Combining Supervised and
Bandit Feedback},
booktitle = {Proceedings of the 36th International Conference on Machine Learning,
{ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {97},
pages = {7335--7344},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/zhang19b.html},
timestamp = {Tue, 11 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZhangAD0N19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GroverSKTAHE19,
author = {Aditya Grover and
Jiaming Song and
Ashish Kapoor and
Kenneth Tran and
Alekh Agarwal and
Eric Horvitz and
Stefano Ermon},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Bias Correction of Learned Generative Models using Likelihood-Free
Importance Weighting},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {11056--11068},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/d76d8deea9c19cc9aaf2237d2bf2f785-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/GroverSKTAHE19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/LiuSAB19,
author = {Yao Liu and
Adith Swaminathan and
Alekh Agarwal and
Emma Brunskill},
editor = {Amir Globerson and
Ricardo Silva},
title = {Off-Policy Policy Gradient with Stationary Distribution Correction},
booktitle = {Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial
Intelligence, {UAI} 2019, Tel Aviv, Israel, July 22-25, 2019},
series = {Proceedings of Machine Learning Research},
volume = {115},
pages = {1180--1190},
publisher = {{AUAI} Press},
year = {2019},
url = {http://proceedings.mlr.press/v115/liu20a.html},
timestamp = {Tue, 15 Dec 2020 17:40:18 +0100},
biburl = {https://dblp.org/rec/conf/uai/LiuSAB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-00301,
author = {Chicheng Zhang and
Alekh Agarwal and
Hal Daum{\'{e}} III and
John Langford and
Sahand N. Negahban},
title = {Warm-starting Contextual Bandits: Robustly Combining Supervised and
Bandit Feedback},
journal = {CoRR},
volume = {abs/1901.00301},
year = {2019},
url = {http://arxiv.org/abs/1901.00301},
eprinttype = {arXiv},
eprint = {1901.00301},
timestamp = {Thu, 31 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-00301.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-09018,
author = {Simon S. Du and
Akshay Krishnamurthy and
Nan Jiang and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
John Langford},
title = {Provably efficient {RL} with Rich Observations via Latent State Decoding},
journal = {CoRR},
volume = {abs/1901.09018},
year = {2019},
url = {http://arxiv.org/abs/1901.09018},
eprinttype = {arXiv},
eprint = {1901.09018},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-09018.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-08473,
author = {Yao Liu and
Adith Swaminathan and
Alekh Agarwal and
Emma Brunskill},
title = {Off-Policy Policy Gradient with State Distribution Correction},
journal = {CoRR},
volume = {abs/1904.08473},
year = {2019},
url = {http://arxiv.org/abs/1904.08473},
eprinttype = {arXiv},
eprint = {1904.08473},
timestamp = {Sat, 14 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-08473.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-05179,
author = {Aditya Modi and
Debadeepta Dey and
Alekh Agarwal and
Adith Swaminathan and
Besmira Nushi and
Sean Andrist and
Eric Horvitz},
title = {Metareasoning in Modular Software Systems: On-the-Fly Configuration
using Reinforcement Learning with Rich Contextual Representations},
journal = {CoRR},
volume = {abs/1905.05179},
year = {2019},
url = {http://arxiv.org/abs/1905.05179},
eprinttype = {arXiv},
eprint = {1905.05179},
timestamp = {Fri, 31 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-05179.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-12843,
author = {Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
Zhiwei Steven Wu},
title = {Fair Regression: Quantitative Definitions and Reduction-based Algorithms},
journal = {CoRR},
volume = {abs/1905.12843},
year = {2019},
url = {http://arxiv.org/abs/1905.12843},
eprinttype = {arXiv},
eprint = {1905.12843},
timestamp = {Mon, 03 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-12843.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-03671,
author = {Jordan T. Ash and
Chicheng Zhang and
Akshay Krishnamurthy and
John Langford and
Alekh Agarwal},
title = {Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds},
journal = {CoRR},
volume = {abs/1906.03671},
year = {2019},
url = {http://arxiv.org/abs/1906.03671},
eprinttype = {arXiv},
eprint = {1906.03671},
timestamp = {Fri, 14 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-03671.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-03804,
author = {Alekh Agarwal and
Sham M. Kakade and
Lin F. Yang},
title = {On the Optimality of Sparse Model-Based Planning for Markov Decision
Processes},
journal = {CoRR},
volume = {abs/1906.03804},
year = {2019},
url = {http://arxiv.org/abs/1906.03804},
eprinttype = {arXiv},
eprint = {1906.03804},
timestamp = {Tue, 23 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-03804.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-09531,
author = {Aditya Grover and
Jiaming Song and
Alekh Agarwal and
Kenneth Tran and
Ashish Kapoor and
Eric Horvitz and
Stefano Ermon},
title = {Bias Correction of Learned Generative Models using Likelihood-Free
Importance Weighting},
journal = {CoRR},
volume = {abs/1906.09531},
year = {2019},
url = {http://arxiv.org/abs/1906.09531},
eprinttype = {arXiv},
eprint = {1906.09531},
timestamp = {Fri, 28 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-09531.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-00261,
author = {Alekh Agarwal and
Sham M. Kakade and
Jason D. Lee and
Gaurav Mahajan},
title = {Optimality and Approximation with Policy Gradient Methods in Markov
Decision Processes},
journal = {CoRR},
volume = {abs/1908.00261},
year = {2019},
url = {http://arxiv.org/abs/1908.00261},
eprinttype = {arXiv},
eprint = {1908.00261},
timestamp = {Fri, 09 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-00261.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/LuoWA018,
author = {Haipeng Luo and
Chen{-}Yu Wei and
Alekh Agarwal and
John Langford},
editor = {S{\'{e}}bastien Bubeck and
Vianney Perchet and
Philippe Rigollet},
title = {Efficient Contextual Bandits in Non-stationary Worlds},
booktitle = {Conference On Learning Theory, {COLT} 2018, Stockholm, Sweden, 6-9
July 2018},
series = {Proceedings of Machine Learning Research},
volume = {75},
pages = {1739--1776},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v75/luo18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:23 +0200},
biburl = {https://dblp.org/rec/conf/colt/LuoWA018.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/JiangA18,
author = {Nan Jiang and
Alekh Agarwal},
editor = {S{\'{e}}bastien Bubeck and
Vianney Perchet and
Philippe Rigollet},
title = {Open Problem: The Dependence of Sample Complexity Lower Bounds on
Planning Horizon},
booktitle = {Conference On Learning Theory, {COLT} 2018, Stockholm, Sweden, 6-9
July 2018},
series = {Proceedings of Machine Learning Research},
volume = {75},
pages = {3395--3398},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v75/jiang18a.html},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/JiangA18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AgarwalBD0W18,
author = {Alekh Agarwal and
Alina Beygelzimer and
Miroslav Dud{\'{\i}}k and
John Langford and
Hanna M. Wallach},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {A Reductions Approach to Fair Classification},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {60--69},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/agarwal18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:30 +0200},
biburl = {https://dblp.org/rec/conf/icml/AgarwalBD0W18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/FosterADLS18,
author = {Dylan J. Foster and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
Haipeng Luo and
Robert E. Schapire},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Practical Contextual Bandits with Regression Oracles},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {1534--1543},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/foster18a.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/FosterADLS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/0001JADYD18,
author = {Hoang Minh Le and
Nan Jiang and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
Yisong Yue and
Hal Daum{\'{e}} III},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Hierarchical Imitation and Reinforcement Learning},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {2923--2932},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/le18a.html},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/0001JADYD18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/DannJKA0S18,
author = {Christoph Dann and
Nan Jiang and
Akshay Krishnamurthy and
Alekh Agarwal and
John Langford and
Robert E. Schapire},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {On Oracle-Efficient {PAC} {RL} with Rich Observations},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {1429--1439},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/5f0f5e5f33945135b874349cfbed4fb9-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/DannJKA0S18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-04064,
author = {Alberto Bietti and
Alekh Agarwal and
John Langford},
title = {Practical Evaluation and Optimization of Contextual Bandit Algorithms},
journal = {CoRR},
volume = {abs/1802.04064},
year = {2018},
url = {http://arxiv.org/abs/1802.04064},
eprinttype = {arXiv},
eprint = {1802.04064},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-04064.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-00590,
author = {Hoang Minh Le and
Nan Jiang and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
Yisong Yue and
Hal Daum{\'{e}} III},
title = {Hierarchical Imitation and Reinforcement Learning},
journal = {CoRR},
volume = {abs/1803.00590},
year = {2018},
url = {http://arxiv.org/abs/1803.00590},
eprinttype = {arXiv},
eprint = {1803.00590},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-00590.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-00606,
author = {Christoph Dann and
Nan Jiang and
Akshay Krishnamurthy and
Alekh Agarwal and
John Langford and
Robert E. Schapire},
title = {On Polynomial Time {PAC} Reinforcement Learning with Rich Observations},
journal = {CoRR},
volume = {abs/1803.00606},
year = {2018},
url = {http://arxiv.org/abs/1803.00606},
eprinttype = {arXiv},
eprint = {1803.00606},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-00606.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-01088,
author = {Dylan J. Foster and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
Haipeng Luo and
Robert E. Schapire},
title = {Practical Contextual Bandits with Regression Oracles},
journal = {CoRR},
volume = {abs/1803.01088},
year = {2018},
url = {http://arxiv.org/abs/1803.01088},
eprinttype = {arXiv},
eprint = {1803.01088},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-01088.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-02453,
author = {Alekh Agarwal and
Alina Beygelzimer and
Miroslav Dud{\'{\i}}k and
John Langford and
Hanna M. Wallach},
title = {A Reductions Approach to Fair Classification},
journal = {CoRR},
volume = {abs/1803.02453},
year = {2018},
url = {http://arxiv.org/abs/1803.02453},
eprinttype = {arXiv},
eprint = {1803.02453},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-02453.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-08540,
author = {Wen Sun and
Nan Jiang and
Akshay Krishnamurthy and
Alekh Agarwal and
John Langford},
title = {Model-Based Reinforcement Learning in Contextual Decision Processes},
journal = {CoRR},
volume = {abs/1811.08540},
year = {2018},
url = {http://arxiv.org/abs/1811.08540},
eprinttype = {arXiv},
eprint = {1811.08540},
timestamp = {Thu, 17 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-08540.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tit/AgarwalAN17,
author = {Alekh Agarwal and
Animashree Anandkumar and
Praneeth Netrapalli},
title = {A Clustering Approach to Learning Sparsely Used Overcomplete Dictionaries},
journal = {{IEEE} Trans. Inf. Theory},
volume = {63},
number = {1},
pages = {575--592},
year = {2017},
url = {https://doi.org/10.1109/TIT.2016.2614684},
doi = {10.1109/TIT.2016.2614684},
timestamp = {Tue, 10 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tit/AgarwalAN17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalKLLS17,
author = {Alekh Agarwal and
Akshay Krishnamurthy and
John Langford and
Haipeng Luo and
Robert E. Schapire},
editor = {Satyen Kale and
Ohad Shamir},
title = {Open Problem: First-Order Regret Bounds for Contextual Bandits},
booktitle = {Proceedings of the 30th Conference on Learning Theory, {COLT} 2017,
Amsterdam, The Netherlands, 7-10 July 2017},
series = {Proceedings of Machine Learning Research},
volume = {65},
pages = {4--7},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v65/agarwal17a.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/colt/AgarwalKLLS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalLNS17,
author = {Alekh Agarwal and
Haipeng Luo and
Behnam Neyshabur and
Robert E. Schapire},
editor = {Satyen Kale and
Ohad Shamir},
title = {Corralling a Band of Bandit Algorithms},
booktitle = {Proceedings of the 30th Conference on Learning Theory, {COLT} 2017,
Amsterdam, The Netherlands, 7-10 July 2017},
series = {Proceedings of Machine Learning Research},
volume = {65},
pages = {12--38},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v65/agarwal17b.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/AgarwalLNS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/JiangKALS17,
author = {Nan Jiang and
Akshay Krishnamurthy and
Alekh Agarwal and
John Langford and
Robert E. Schapire},
editor = {Doina Precup and
Yee Whye Teh},
title = {Contextual Decision Processes with low Bellman rank are PAC-Learnable},
booktitle = {Proceedings of the 34th International Conference on Machine Learning,
{ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017},
series = {Proceedings of Machine Learning Research},
volume = {70},
pages = {1704--1713},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/jiang17c.html},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/JiangKALS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KrishnamurthyAH17,
author = {Akshay Krishnamurthy and
Alekh Agarwal and
Tzu{-}Kuo Huang and
Hal Daum{\'{e}} III and
John Langford},
editor = {Doina Precup and
Yee Whye Teh},
title = {Active Learning for Cost-Sensitive Classification},
booktitle = {Proceedings of the 34th International Conference on Machine Learning,
{ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017},
series = {Proceedings of Machine Learning Research},
volume = {70},
pages = {1915--1924},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/krishnamurthy17a.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/KrishnamurthyAH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WangAD17,
author = {Yu{-}Xiang Wang and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k},
editor = {Doina Precup and
Yee Whye Teh},
title = {Optimal and Adaptive Off-policy Evaluation in Contextual Bandits},
booktitle = {Proceedings of the 34th International Conference on Machine Learning,
{ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017},
series = {Proceedings of Machine Learning Research},
volume = {70},
pages = {3589--3597},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/wang17a.html},
timestamp = {Thu, 30 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WangAD17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SwaminathanKADL17,
author = {Adith Swaminathan and
Akshay Krishnamurthy and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
John Langford and
Damien Jose and
Imed Zitouni},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Off-policy evaluation for slate recommendation},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {3632--3642},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/5352696a9ca3397beb79f116f3a33991-Abstract.html},
timestamp = {Thu, 21 Jan 2021 13:58:27 +0100},
biburl = {https://dblp.org/rec/conf/nips/SwaminathanKADL17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KrishnamurthyAH17,
author = {Akshay Krishnamurthy and
Alekh Agarwal and
Tzu{-}Kuo Huang and
Hal Daum{\'{e}} III and
John Langford},
title = {Active Learning for Cost-Sensitive Classification},
journal = {CoRR},
volume = {abs/1703.01014},
year = {2017},
url = {http://arxiv.org/abs/1703.01014},
eprinttype = {arXiv},
eprint = {1703.01014},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KrishnamurthyAH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-01799,
author = {Haipeng Luo and
Alekh Agarwal and
John Langford},
title = {Efficient Contextual Bandits in Non-stationary Worlds},
journal = {CoRR},
volume = {abs/1708.01799},
year = {2017},
url = {http://arxiv.org/abs/1708.01799},
eprinttype = {arXiv},
eprint = {1708.01799},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-01799.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/siamjo/AgarwalAJN16,
author = {Alekh Agarwal and
Animashree Anandkumar and
Prateek Jain and
Praneeth Netrapalli},
title = {Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization},
journal = {{SIAM} J. Optim.},
volume = {26},
number = {4},
pages = {2775--2799},
year = {2016},
url = {https://doi.org/10.1137/140979861},
doi = {10.1137/140979861},
timestamp = {Mon, 08 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/siamjo/AgarwalAJN16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LuoACL16,
author = {Haipeng Luo and
Alekh Agarwal and
Nicol{\`{o}} Cesa{-}Bianchi and
John Langford},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {Efficient Second Order Online Learning by Sketching},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {902--910},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/15de21c670ae7c3f6f3f1f37029303c9-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/LuoACL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KrishnamurthyAL16,
author = {Akshay Krishnamurthy and
Alekh Agarwal and
John Langford},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {{PAC} Reinforcement Learning with Rich Observations},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {1840--1848},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/2387337ba1e0b0249ba90f55b2ba2521-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/KrishnamurthyAL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KrishnamurthyAD16,
author = {Akshay Krishnamurthy and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {Contextual semibandits via supervised learning oracles},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {2388--2396},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/e1d5be1c7f2f456670de3d53c7b54f4a-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/KrishnamurthyAD16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LuoACL16,
author = {Haipeng Luo and
Alekh Agarwal and
Nicol{\`{o}} Cesa{-}Bianchi and
John Langford},
title = {Efficient Second Order Online Learning via Sketching},
journal = {CoRR},
volume = {abs/1602.02202},
year = {2016},
url = {http://arxiv.org/abs/1602.02202},
eprinttype = {arXiv},
eprint = {1602.02202},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LuoACL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KrishnamurthyAL16,
author = {Akshay Krishnamurthy and
Alekh Agarwal and
John Langford},
title = {Contextual-MDPs for PAC-Reinforcement Learning with Rich Observations},
journal = {CoRR},
volume = {abs/1602.02722},
year = {2016},
url = {http://arxiv.org/abs/1602.02722},
eprinttype = {arXiv},
eprint = {1602.02722},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KrishnamurthyAL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AbelADKS16,
author = {David Abel and
Alekh Agarwal and
Fernando Diaz and
Akshay Krishnamurthy and
Robert E. Schapire},
title = {Exploratory Gradient Boosting for Reinforcement Learning in Complex
Domains},
journal = {CoRR},
volume = {abs/1603.04119},
year = {2016},
url = {http://arxiv.org/abs/1603.04119},
eprinttype = {arXiv},
eprint = {1603.04119},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AbelADKS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SwaminathanKADL16,
author = {Adith Swaminathan and
Akshay Krishnamurthy and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
John Langford and
Damien Jose and
Imed Zitouni},
title = {Off-policy evaluation for slate recommendation},
journal = {CoRR},
volume = {abs/1605.04812},
year = {2016},
url = {http://arxiv.org/abs/1605.04812},
eprinttype = {arXiv},
eprint = {1605.04812},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SwaminathanKADL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AgarwalBCHLLLMO16,
author = {Alekh Agarwal and
Sarah Bird and
Markus Cozowicz and
Luong Hoang and
John Langford and
Stephen Lee and
Jiaji Li and
I. Dan Melamed and
Gal Oshri and
Oswaldo Ribas and
Siddhartha Sen and
Alex Slivkins},
title = {A Multiworld Testing Decision Service},
journal = {CoRR},
volume = {abs/1606.03966},
year = {2016},
url = {http://arxiv.org/abs/1606.03966},
eprinttype = {arXiv},
eprint = {1606.03966},
timestamp = {Thu, 01 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AgarwalBCHLLLMO16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/JiangKALS16,
author = {Nan Jiang and
Akshay Krishnamurthy and
Alekh Agarwal and
John Langford and
Robert E. Schapire},
title = {Contextual Decision Processes with Low Bellman Rank are PAC-Learnable},
journal = {CoRR},
volume = {abs/1610.09512},
year = {2016},
url = {http://arxiv.org/abs/1610.09512},
eprinttype = {arXiv},
eprint = {1610.09512},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/JiangKALS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangAD16,
author = {Yu{-}Xiang Wang and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k},
title = {Optimal and Adaptive Off-policy Evaluation in Contextual Bandits},
journal = {CoRR},
volume = {abs/1612.01205},
year = {2016},
url = {http://arxiv.org/abs/1612.01205},
eprinttype = {arXiv},
eprint = {1612.01205},
timestamp = {Thu, 30 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WangAD16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AgarwalLNS16,
author = {Alekh Agarwal and
Haipeng Luo and
Behnam Neyshabur and
Robert E. Schapire},
title = {Corralling a Band of Bandit Algorithms},
journal = {CoRR},
volume = {abs/1612.06246},
year = {2016},
url = {http://arxiv.org/abs/1612.06246},
eprinttype = {arXiv},
eprint = {1612.06246},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AgarwalLNS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AgarwalB15,
author = {Alekh Agarwal and
L{\'{e}}on Bottou},
editor = {Francis R. Bach and
David M. Blei},
title = {A Lower Bound for the Optimization of Finite Sums},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {78--86},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/agarwal15.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/AgarwalB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ChangKADL15,
author = {Kai{-}Wei Chang and
Akshay Krishnamurthy and
Alekh Agarwal and
Hal Daum{\'{e}} III and
John Langford},
editor = {Francis R. Bach and
David M. Blei},
title = {Learning to Search Better than Your Teacher},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {2058--2066},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/changb15.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ChangKADL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HuangAHLS15,
author = {Tzu{-}Kuo Huang and
Alekh Agarwal and
Daniel J. Hsu and
John Langford and
Robert E. Schapire},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Efficient and Parsimonious Agnostic Active Learning},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {2755--2763},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/0d4f4805c36dc6853edfa4c7e1638b48-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/HuangAHLS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SyrgkanisALS15,
author = {Vasilis Syrgkanis and
Alekh Agarwal and
Haipeng Luo and
Robert E. Schapire},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Fast Convergence of Regularized Learning in Games},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {2989--2997},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/7fea637fd6d02b8f0adf6f7dc36aed93-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/SyrgkanisALS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ChangKADL15,
author = {Kai{-}Wei Chang and
Akshay Krishnamurthy and
Alekh Agarwal and
Hal Daum{\'{e}} III and
John Langford},
title = {Learning to Search Better Than Your Teacher},
journal = {CoRR},
volume = {abs/1502.02206},
year = {2015},
url = {http://arxiv.org/abs/1502.02206},
eprinttype = {arXiv},
eprint = {1502.02206},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ChangKADL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KrishnamurthyAD15,
author = {Akshay Krishnamurthy and
Alekh Agarwal and
Miroslav Dud{\'{\i}}k},
title = {Efficient Contextual Semi-Bandit Learning},
journal = {CoRR},
volume = {abs/1502.05890},
year = {2015},
url = {http://arxiv.org/abs/1502.05890},
eprinttype = {arXiv},
eprint = {1502.05890},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KrishnamurthyAD15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HuangAHLS15,
author = {Tzu{-}Kuo Huang and
Alekh Agarwal and
Daniel J. Hsu and
John Langford and
Robert E. Schapire},
title = {Efficient and Parsimonious Agnostic Active Learning},
journal = {CoRR},
volume = {abs/1506.08669},
year = {2015},
url = {http://arxiv.org/abs/1506.08669},
eprinttype = {arXiv},
eprint = {1506.08669},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HuangAHLS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SyrgkanisALS15,
author = {Vasilis Syrgkanis and
Alekh Agarwal and
Haipeng Luo and
Robert E. Schapire},
title = {Fast Convergence of Regularized Learning in Games},
journal = {CoRR},
volume = {abs/1507.00407},
year = {2015},
url = {http://arxiv.org/abs/1507.00407},
eprinttype = {arXiv},
eprint = {1507.00407},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SyrgkanisALS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/AgarwalCDL14,
author = {Alekh Agarwal and
Olivier Chapelle and
Miroslav Dud{\'{\i}}k and
John Langford},
title = {A reliable effective terascale linear learning system},
journal = {J. Mach. Learn. Res.},
volume = {15},
number = {1},
pages = {1111--1133},
year = {2014},
url = {https://dl.acm.org/doi/10.5555/2627435.2638571},
doi = {10.5555/2627435.2638571},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/AgarwalCDL14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ciss/AgarwalNW14,
author = {Alekh Agarwal and
Sahand N. Negahban and
Martin J. Wainwright},
title = {Stochastic optimization and sparse statistical recovery: An optimal
algorithm for high dimensions},
booktitle = {48th Annual Conference on Information Sciences and Systems, {CISS}
2014, Princeton, NJ, USA, March 19-21, 2014},
pages = {1--2},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/CISS.2014.6814157},
doi = {10.1109/CISS.2014.6814157},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/ciss/AgarwalNW14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalA0NT14,
author = {Alekh Agarwal and
Animashree Anandkumar and
Prateek Jain and
Praneeth Netrapalli and
Rashish Tandon},
editor = {Maria{-}Florina Balcan and
Vitaly Feldman and
Csaba Szepesv{\'{a}}ri},
title = {Learning Sparsely Used Overcomplete Dictionaries},
booktitle = {Proceedings of The 27th Conference on Learning Theory, {COLT} 2014,
Barcelona, Spain, June 13-15, 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {35},
pages = {123--137},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v35/agarwal14a.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/colt/AgarwalA0NT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalBDSS14,
author = {Alekh Agarwal and
Ashwinkumar Badanidiyuru and
Miroslav Dud{\'{\i}}k and
Robert E. Schapire and
Aleksandrs Slivkins},
editor = {Maria{-}Florina Balcan and
Vitaly Feldman and
Csaba Szepesv{\'{a}}ri},
title = {Robust Multi-objective Learning with Mentor Feedback},
booktitle = {Proceedings of The 27th Conference on Learning Theory, {COLT} 2014,
Barcelona, Spain, June 13-15, 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {35},
pages = {726--741},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v35/agarwal14b.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/AgarwalBDSS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AgarwalKKSV14,
author = {Alekh Agarwal and
Sham M. Kakade and
Nikos Karampatziakis and
Le Song and
Gregory Valiant},
title = {Least Squares Revisited: Scalable Approaches for Multi-class Prediction},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {541--549},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/agarwala14.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/AgarwalKKSV14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AgarwalHKLLS14,
author = {Alekh Agarwal and
Daniel J. Hsu and
Satyen Kale and
John Langford and
Lihong Li and
Robert E. Schapire},
title = {Taming the Monster: {A} Fast and Simple Algorithm for Contextual Bandits},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {1638--1646},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/agarwalb14.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/AgarwalHKLLS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AgarwalBHLT14,
author = {Alekh Agarwal and
Alina Beygelzimer and
Daniel J. Hsu and
John Langford and
Matus Telgarsky},
editor = {Zoubin Ghahramani and
Max Welling and
Corinna Cortes and
Neil D. Lawrence and
Kilian Q. Weinberger},
title = {Scalable Non-linear Learning with Adaptive Polynomial Expansions},
booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference
on Neural Information Processing Systems 2014, December 8-13 2014,
Montreal, Quebec, Canada},
pages = {2051--2059},
year = {2014},
url = {https://proceedings.neurips.cc/paper/2014/hash/8f1d43620bc6bb580df6e80b0dc05c48-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/AgarwalBHLT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AgarwalHKLLS14,
author = {Alekh Agarwal and
Daniel J. Hsu and
Satyen Kale and
John Langford and
Lihong Li and
Robert E. Schapire},
title = {Taming the Monster: {A} Fast and Simple Algorithm for Contextual Bandits},
journal = {CoRR},
volume = {abs/1402.0555},
year = {2014},
url = {http://arxiv.org/abs/1402.0555},
eprinttype = {arXiv},
eprint = {1402.0555},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AgarwalHKLLS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AgarwalBHLT14,
author = {Alekh Agarwal and
Alina Beygelzimer and
Daniel J. Hsu and
John Langford and
Matus Telgarsky},
title = {Scalable Nonlinear Learning with Adaptive Polynomial Expansions},
journal = {CoRR},
volume = {abs/1410.0440},
year = {2014},
url = {http://arxiv.org/abs/1410.0440},
eprinttype = {arXiv},
eprint = {1410.0440},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AgarwalBHLT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/siamjo/AgarwalFHKR13,
author = {Alekh Agarwal and
Dean P. Foster and
Daniel J. Hsu and
Sham M. Kakade and
Alexander Rakhlin},
title = {Stochastic Convex Optimization with Bandit Feedback},
journal = {{SIAM} J. Optim.},
volume = {23},
number = {1},
pages = {213--240},
year = {2013},
url = {https://doi.org/10.1137/110850827},
doi = {10.1137/110850827},
timestamp = {Mon, 08 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/siamjo/AgarwalFHKR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tit/AgarwalD13,
author = {Alekh Agarwal and
John C. Duchi},
title = {The Generalization Ability of Online Algorithms for Dependent Data},
journal = {{IEEE} Trans. Inf. Theory},
volume = {59},
number = {1},
pages = {573--587},
year = {2013},
url = {https://doi.org/10.1109/TIT.2012.2212414},
doi = {10.1109/TIT.2012.2212414},
timestamp = {Tue, 10 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tit/AgarwalD13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/Agarwal13,
author = {Alekh Agarwal},
title = {Selective sampling algorithms for cost-sensitive multiclass prediction},
booktitle = {Proceedings of the 30th International Conference on Machine Learning,
{ICML} 2013, Atlanta, GA, USA, 16-21 June 2013},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {28},
pages = {1220--1228},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v28/agarwal13.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/Agarwal13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AgarwalAN13,
author = {Alekh Agarwal and
Animashree Anandkumar and
Praneeth Netrapalli},
title = {Exact Recovery of Sparsely Used Overcomplete Dictionaries},
journal = {CoRR},
volume = {abs/1309.1952},
year = {2013},
url = {http://arxiv.org/abs/1309.1952},
eprinttype = {arXiv},
eprint = {1309.1952},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AgarwalAN13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AgarwalKKSV13,
author = {Alekh Agarwal and
Sham M. Kakade and
Nikos Karampatziakis and
Le Song and
Gregory Valiant},
title = {Least Squares Revisited: Scalable Approaches for Multi-class Prediction},
journal = {CoRR},
volume = {abs/1310.1949},
year = {2013},
url = {http://arxiv.org/abs/1310.1949},
eprinttype = {arXiv},
eprint = {1310.1949},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AgarwalKKSV13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AgarwalA0NT13,
author = {Alekh Agarwal and
Animashree Anandkumar and
Prateek Jain and
Praneeth Netrapalli and
Rashish Tandon},
title = {Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization},
journal = {CoRR},
volume = {abs/1310.7991},
year = {2013},
url = {http://arxiv.org/abs/1310.7991},
eprinttype = {arXiv},
eprint = {1310.7991},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AgarwalA0NT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AgarwalBDL13,
author = {Alekh Agarwal and
L{\'{e}}on Bottou and
Miroslav Dud{\'{\i}}k and
John Langford},
title = {Para-active learning},
journal = {CoRR},
volume = {abs/1310.8243},
year = {2013},
url = {http://arxiv.org/abs/1310.8243},
eprinttype = {arXiv},
eprint = {1310.8243},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AgarwalBDL13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/basesearch/Agarwal12,
author = {Alekh Agarwal},
title = {Computational Trade-offs in Statistical Learning},
school = {University of California, Berkeley, {USA}},
year = {2012},
url = {http://www.escholarship.org/uc/item/1kv80526},
timestamp = {Wed, 19 Apr 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/basesearch/Agarwal12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/siamjo/DuchiAJJ12,
author = {John C. Duchi and
Alekh Agarwal and
Mikael Johansson and
Michael I. Jordan},
title = {Ergodic Mirror Descent},
journal = {{SIAM} J. Optim.},
volume = {22},
number = {4},
pages = {1549--1578},
year = {2012},
url = {https://doi.org/10.1137/110836043},
doi = {10.1137/110836043},
timestamp = {Mon, 15 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/siamjo/DuchiAJJ12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/DuchiAW12,
author = {John C. Duchi and
Alekh Agarwal and
Martin J. Wainwright},
title = {Dual Averaging for Distributed Optimization: Convergence Analysis
and Network Scaling},
journal = {{IEEE} Trans. Autom. Control.},
volume = {57},
number = {3},
pages = {592--606},
year = {2012},
url = {https://doi.org/10.1109/TAC.2011.2161027},
doi = {10.1109/TAC.2011.2161027},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/DuchiAW12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tit/AgarwalBRW12,
author = {Alekh Agarwal and
Peter L. Bartlett and
Pradeep Ravikumar and
Martin J. Wainwright},
title = {Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic
Convex Optimization},
journal = {{IEEE} Trans. Inf. Theory},
volume = {58},
number = {5},
pages = {3235--3249},
year = {2012},
url = {https://doi.org/10.1109/TIT.2011.2182178},
doi = {10.1109/TIT.2011.2182178},
timestamp = {Tue, 01 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tit/AgarwalBRW12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/DuchiAW12,
author = {John C. Duchi and
Alekh Agarwal and
Martin J. Wainwright},
title = {Dual averaging for distributed optimization},
booktitle = {50th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2012, Allerton Park {\&} Retreat Center, Monticello,
IL, USA, October 1-5, 2012},
pages = {1564--1565},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/Allerton.2012.6483406},
doi = {10.1109/ALLERTON.2012.6483406},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/allerton/DuchiAW12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/AgarwalD12,
author = {Alekh Agarwal and
John C. Duchi},
title = {Distributed delayed stochastic optimization},
booktitle = {Proceedings of the 51th {IEEE} Conference on Decision and Control,
{CDC} 2012, December 10-13, 2012, Maui, HI, {USA}},
pages = {5451--5452},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/CDC.2012.6426626},
doi = {10.1109/CDC.2012.6426626},
timestamp = {Fri, 04 Mar 2022 13:28:47 +0100},
biburl = {https://dblp.org/rec/conf/cdc/AgarwalD12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AgarwalNW12,
author = {Alekh Agarwal and
Sahand N. Negahban and
Martin J. Wainwright},
editor = {Peter L. Bartlett and
Fernando C. N. Pereira and
Christopher J. C. Burges and
L{\'{e}}on Bottou and
Kilian Q. Weinberger},
title = {Stochastic optimization and sparse statistical recovery: Optimal algorithms
for high dimensions},
booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual
Conference on Neural Information Processing Systems 2012. Proceedings
of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States},
pages = {1547--1555},
year = {2012},
url = {https://proceedings.neurips.cc/paper/2012/hash/5751ec3e9a4feab575962e78e006250d-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/AgarwalNW12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ssp/AgarwalNW12,
author = {Alekh Agarwal and
Sahand N. Negahban and
Martin J. Wainwright},
title = {FASt global convergence of gradient methods for solving regularized
M-estimation},
booktitle = {{IEEE} Statistical Signal Processing Workshop, {SSP} 2012, Ann Arbor,
MI, USA, August 5-8, 2012},
pages = {409--412},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/SSP.2012.6319717},
doi = {10.1109/SSP.2012.6319717},
timestamp = {Wed, 16 Oct 2019 14:14:54 +0200},
biburl = {https://dblp.org/rec/conf/ssp/AgarwalNW12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/AgarwalDKLS12,
author = {Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
Satyen Kale and
John Langford and
Robert E. Schapire},
editor = {Neil D. Lawrence and
Mark A. Girolami},
title = {Contextual Bandit Learning with Predictable Rewards},
booktitle = {Proceedings of the Fifteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2012, La Palma, Canary Islands,
Spain, April 21-23, 2012},
series = {{JMLR} Proceedings},
volume = {22},
pages = {19--26},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v22/agarwal12.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/AgarwalDKLS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1202-1334,
author = {Alekh Agarwal and
Miroslav Dud{\'{\i}}k and
Satyen Kale and
John Langford and
Robert E. Schapire},
title = {Contextual Bandit Learning with Predictable Rewards},
journal = {CoRR},
volume = {abs/1202.1334},
year = {2012},
url = {http://arxiv.org/abs/1202.1334},
eprinttype = {arXiv},
eprint = {1202.1334},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1202-1334.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1207-4421,
author = {Alekh Agarwal and
Sahand N. Negahban and
Martin J. Wainwright},
title = {Stochastic optimization and sparse statistical recovery: An optimal
algorithm for high dimensions},
journal = {CoRR},
volume = {abs/1207.4421},
year = {2012},
url = {http://arxiv.org/abs/1207.4421},
eprinttype = {arXiv},
eprint = {1207.4421},
timestamp = {Thu, 31 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1207-4421.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1208-0129,
author = {Alekh Agarwal and
Peter L. Bartlett and
John C. Duchi},
title = {Oracle inequalities for computationally adaptive model selection},
journal = {CoRR},
volume = {abs/1208.0129},
year = {2012},
url = {http://arxiv.org/abs/1208.0129},
eprinttype = {arXiv},
eprint = {1208.0129},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1208-0129.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/DuchiAJJ11,
author = {John C. Duchi and
Alekh Agarwal and
Mikael Johansson and
Michael I. Jordan},
title = {Ergodic mirror descent},
booktitle = {49th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2011, Allerton Park {\&} Retreat Center, Monticello,
IL, USA, 28-30 September, 2011},
pages = {701--706},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/Allerton.2011.6120236},
doi = {10.1109/ALLERTON.2011.6120236},
timestamp = {Mon, 15 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/allerton/DuchiAJJ11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AgarwalNW11,
author = {Alekh Agarwal and
Sahand N. Negahban and
Martin J. Wainwright},
editor = {Lise Getoor and
Tobias Scheffer},
title = {Noisy matrix decomposition via convex relaxation: Optimal rates in
high dimensions},
booktitle = {Proceedings of the 28th International Conference on Machine Learning,
{ICML} 2011, Bellevue, Washington, USA, June 28 - July 2, 2011},
pages = {1129--1136},
publisher = {Omnipress},
year = {2011},
url = {https://icml.cc/2011/papers/572\_icmlpaper.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/AgarwalNW11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AgarwalD11,
author = {Alekh Agarwal and
John C. Duchi},
editor = {John Shawe{-}Taylor and
Richard S. Zemel and
Peter L. Bartlett and
Fernando C. N. Pereira and
Kilian Q. Weinberger},
title = {Distributed Delayed Stochastic Optimization},
booktitle = {Advances in Neural Information Processing Systems 24: 25th Annual
Conference on Neural Information Processing Systems 2011. Proceedings
of a meeting held 12-14 December 2011, Granada, Spain},
pages = {873--881},
year = {2011},
url = {https://proceedings.neurips.cc/paper/2011/hash/f0e52b27a7a5d6a1a87373dffa53dbe5-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/AgarwalD11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AgarwalFHKR11,
author = {Alekh Agarwal and
Dean P. Foster and
Daniel J. Hsu and
Sham M. Kakade and
Alexander Rakhlin},
editor = {John Shawe{-}Taylor and
Richard S. Zemel and
Peter L. Bartlett and
Fernando C. N. Pereira and
Kilian Q. Weinberger},
title = {Stochastic convex optimization with bandit feedback},
booktitle = {Advances in Neural Information Processing Systems 24: 25th Annual
Conference on Neural Information Processing Systems 2011. Proceedings
of a meeting held 12-14 December 2011, Granada, Spain},
pages = {1035--1043},
year = {2011},
url = {https://proceedings.neurips.cc/paper/2011/hash/67e103b0761e60683e83c559be18d40c-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/AgarwalFHKR11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/RostamizadehAB11,
author = {Afshin Rostamizadeh and
Alekh Agarwal and
Peter L. Bartlett},
editor = {F{\'{a}}bio Gagliardi Cozman and
Avi Pfeffer},
title = {Learning with Missing Features},
booktitle = {{UAI} 2011, Proceedings of the Twenty-Seventh Conference on Uncertainty
in Artificial Intelligence, Barcelona, Spain, July 14-17, 2011},
pages = {635--642},
publisher = {{AUAI} Press},
year = {2011},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=2193\&\#38;proceeding\_id=27},
timestamp = {Wed, 03 Feb 2021 11:09:03 +0100},
biburl = {https://dblp.org/rec/conf/uai/RostamizadehAB11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/AgarwalDBL11,
author = {Alekh Agarwal and
John C. Duchi and
Peter L. Bartlett and
Cl{\'{e}}ment Levrard},
editor = {Sham M. Kakade and
Ulrike von Luxburg},
title = {Oracle inequalities for computationally budgeted model selection},
booktitle = {{COLT} 2011 - The 24th Annual Conference on Learning Theory, June
9-11, 2011, Budapest, Hungary},
series = {{JMLR} Proceedings},
volume = {19},
pages = {69--86},
publisher = {JMLR.org},
year = {2011},
url = {http://proceedings.mlr.press/v19/agarwal11a/agarwal11a.pdf},
timestamp = {Wed, 29 May 2019 08:41:47 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/AgarwalDBL11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1102-4807,
author = {Alekh Agarwal and
Sahand N. Negahban and
Martin J. Wainwright},
title = {Noisy matrix decomposition via convex relaxation: Optimal rates in
high dimensions},
journal = {CoRR},
volume = {abs/1102.4807},
year = {2011},
url = {http://arxiv.org/abs/1102.4807},
eprinttype = {arXiv},
eprint = {1102.4807},
timestamp = {Thu, 31 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1102-4807.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1104-0729,
author = {Afshin Rostamizadeh and
Alekh Agarwal and
Peter L. Bartlett},
title = {Online and Batch Learning Algorithms for Data with Missing Features},
journal = {CoRR},
volume = {abs/1104.0729},
year = {2011},
url = {http://arxiv.org/abs/1104.0729},
eprinttype = {arXiv},
eprint = {1104.0729},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1104-0729.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1104-4824,
author = {Alekh Agarwal and
Sahand N. Negahban and
Martin J. Wainwright},
title = {Fast global convergence of gradient methods for high-dimensional statistical
recovery},
journal = {CoRR},
volume = {abs/1104.4824},
year = {2011},
url = {http://arxiv.org/abs/1104.4824},
eprinttype = {arXiv},
eprint = {1104.4824},
timestamp = {Thu, 31 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1104-4824.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1107-1744,
author = {Alekh Agarwal and
Dean P. Foster and
Daniel J. Hsu and
Sham M. Kakade and
Alexander Rakhlin},
title = {Stochastic convex optimization with bandit feedback},
journal = {CoRR},
volume = {abs/1107.1744},
year = {2011},
url = {http://arxiv.org/abs/1107.1744},
eprinttype = {arXiv},
eprint = {1107.1744},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1107-1744.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1110-2529,
author = {Alekh Agarwal and
John C. Duchi},
title = {The Generalization Ability of Online Algorithms for Dependent Data},
journal = {CoRR},
volume = {abs/1110.2529},
year = {2011},
url = {http://arxiv.org/abs/1110.2529},
eprinttype = {arXiv},
eprint = {1110.2529},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1110-2529.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1110-4198,
author = {Alekh Agarwal and
Olivier Chapelle and
Miroslav Dud{\'{\i}}k and
John Langford},
title = {A Reliable Effective Terascale Linear Learning System},
journal = {CoRR},
volume = {abs/1110.4198},
year = {2011},
url = {http://arxiv.org/abs/1110.4198},
eprinttype = {arXiv},
eprint = {1110.4198},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1110-4198.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/RavikumarAW10,
author = {Pradeep Ravikumar and
Alekh Agarwal and
Martin J. Wainwright},
title = {Message-passing for Graph-structured Linear Programs: Proximal Methods
and Rounding Schemes},
journal = {J. Mach. Learn. Res.},
volume = {11},
pages = {1043--1080},
year = {2010},
url = {https://dl.acm.org/doi/10.5555/1756006.1756040},
doi = {10.5555/1756006.1756040},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/RavikumarAW10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AgarwalDX10,
author = {Alekh Agarwal and
Ofer Dekel and
Lin Xiao},
editor = {Adam Tauman Kalai and
Mehryar Mohri},
title = {Optimal Algorithms for Online Convex Optimization with Multi-Point
Bandit Feedback},
booktitle = {{COLT} 2010 - The 23rd Conference on Learning Theory, Haifa, Israel,
June 27-29, 2010},
pages = {28--40},
publisher = {Omnipress},
year = {2010},
url = {http://colt2010.haifa.il.ibm.com/papers/COLT2010proceedings.pdf\#page=36},
timestamp = {Tue, 25 Jan 2022 13:23:33 +0100},
biburl = {https://dblp.org/rec/conf/colt/AgarwalDX10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AgarwalNW10,
author = {Alekh Agarwal and
Sahand N. Negahban and
Martin J. Wainwright},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Fast global convergence rates of gradient methods for high-dimensional
statistical recovery},
booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual
Conference on Neural Information Processing Systems 2010. Proceedings
of a meeting held 6-9 December 2010, Vancouver, British Columbia,
Canada},
pages = {37--45},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/7cce53cf90577442771720a370c3c723-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/AgarwalNW10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/DuchiAW10,
author = {John C. Duchi and
Alekh Agarwal and
Martin J. Wainwright},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Distributed Dual Averaging In Networks},
booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual
Conference on Neural Information Processing Systems 2010. Proceedings
of a meeting held 6-9 December 2010, Vancouver, British Columbia,
Canada},
pages = {550--558},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/faa9afea49ef2ff029a833cccc778fd0-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/DuchiAW10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/AgarwalBD10,
author = {Alekh Agarwal and
Peter L. Bartlett and
Max Dama},
editor = {Yee Whye Teh and
D. Mike Titterington},
title = {Optimal Allocation Strategies for the Dark Pool Problem},
booktitle = {Proceedings of the Thirteenth International Conference on Artificial
Intelligence and Statistics, {AISTATS} 2010, Chia Laguna Resort, Sardinia,
Italy, May 13-15, 2010},
series = {{JMLR} Proceedings},
volume = {9},
pages = {9--16},
publisher = {JMLR.org},
year = {2010},
url = {http://proceedings.mlr.press/v9/agarwal10a.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/AgarwalBD10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AgarwalBRW10,
author = {Alekh Agarwal and
Peter L. Bartlett and
Pradeep Ravikumar and
Martin J. Wainwright},
title = {Information-theoretic lower bounds on the oracle complexity of stochastic
convex optimization},
journal = {CoRR},
volume = {abs/1009.0571},
year = {2010},
url = {http://arxiv.org/abs/1009.0571},
eprinttype = {arXiv},
eprint = {1009.0571},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AgarwalBRW10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AbernethyABR09,
author = {Jacob D. Abernethy and
Alekh Agarwal and
Peter L. Bartlett and
Alexander Rakhlin},
title = {A Stochastic View of Optimal Regret through Minimax Duality},
booktitle = {{COLT} 2009 - The 22nd Conference on Learning Theory, Montreal, Quebec,
Canada, June 18-21, 2009},
year = {2009},
url = {http://www.cs.mcgill.ca/\%7Ecolt2009/papers/026.pdf\#page=1},
timestamp = {Thu, 04 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/AbernethyABR09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AgarwalBRW09,
author = {Alekh Agarwal and
Peter L. Bartlett and
Pradeep Ravikumar and
Martin J. Wainwright},
editor = {Yoshua Bengio and
Dale Schuurmans and
John D. Lafferty and
Christopher K. I. Williams and
Aron Culotta},
title = {Information-theoretic lower bounds on the oracle complexity of convex
optimization},
booktitle = {Advances in Neural Information Processing Systems 22: 23rd Annual
Conference on Neural Information Processing Systems 2009. Proceedings
of a meeting held 7-10 December 2009, Vancouver, British Columbia,
Canada},
pages = {1--9},
publisher = {Curran Associates, Inc.},
year = {2009},
url = {https://proceedings.neurips.cc/paper/2009/hash/2387337ba1e0b0249ba90f55b2ba2521-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/AgarwalBRW09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-0903-5328,
author = {Jacob D. Abernethy and
Alekh Agarwal and
Peter L. Bartlett and
Alexander Rakhlin},
title = {A Stochastic View of Optimal Regret through Minimax Duality},
journal = {CoRR},
volume = {abs/0903.5328},
year = {2009},
url = {http://arxiv.org/abs/0903.5328},
eprinttype = {arXiv},
eprint = {0903.5328},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-0903-5328.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/RavikumarAW08,
author = {Pradeep Ravikumar and
Alekh Agarwal and
Martin J. Wainwright},
editor = {William W. Cohen and
Andrew McCallum and
Sam T. Roweis},
title = {Message-passing for graph-structured linear programs: proximal projections,
convergence and rounding schemes},
booktitle = {Machine Learning, Proceedings of the Twenty-Fifth International Conference
{(ICML} 2008), Helsinki, Finland, June 5-9, 2008},
series = {{ACM} International Conference Proceeding Series},
volume = {307},
pages = {800--807},
publisher = {{ACM}},
year = {2008},
url = {https://doi.org/10.1145/1390156.1390257},
doi = {10.1145/1390156.1390257},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/RavikumarAW08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AgarwalC07,
author = {Alekh Agarwal and
Soumen Chakrabarti},
editor = {Zoubin Ghahramani},
title = {Learning random walks to rank nodes in graphs},
booktitle = {Machine Learning, Proceedings of the Twenty-Fourth International Conference
{(ICML} 2007), Corvallis, Oregon, USA, June 20-24, 2007},
series = {{ACM} International Conference Proceeding Series},
volume = {227},
pages = {9--16},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1273496.1273498},
doi = {10.1145/1273496.1273498},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/AgarwalC07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SinzCAS07,
author = {Fabian H. Sinz and
Olivier Chapelle and
Alekh Agarwal and
Bernhard Sch{\"{o}}lkopf},
editor = {John C. Platt and
Daphne Koller and
Yoram Singer and
Sam T. Roweis},
title = {An Analysis of Inference with the Universum},
booktitle = {Advances in Neural Information Processing Systems 20, Proceedings
of the Twenty-First Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 3-6, 2007},
pages = {1369--1376},
publisher = {Curran Associates, Inc.},
year = {2007},
url = {https://proceedings.neurips.cc/paper/2007/hash/a8e864d04c95572d1aece099af852d0a-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/SinzCAS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kdd/AgarwalCA06,
author = {Alekh Agarwal and
Soumen Chakrabarti and
Sunny Aggarwal},
editor = {Tina Eliassi{-}Rad and
Lyle H. Ungar and
Mark Craven and
Dimitrios Gunopulos},
title = {Learning to rank networked entities},
booktitle = {Proceedings of the Twelfth {ACM} {SIGKDD} International Conference
on Knowledge Discovery and Data Mining, Philadelphia, PA, USA, August
20-23, 2006},
pages = {14--23},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1150402.1150409},
doi = {10.1145/1150402.1150409},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/kdd/AgarwalCA06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/ChakrabartiA06,
author = {Soumen Chakrabarti and
Alekh Agarwal},
editor = {Johannes F{\"{u}}rnkranz and
Tobias Scheffer and
Myra Spiliopoulou},
title = {Learning Parameters in Entity Relationship Graphs from Ranking Preferences},
booktitle = {Knowledge Discovery in Databases: {PKDD} 2006, 10th European Conference
on Principles and Practice of Knowledge Discovery in Databases, Berlin,
Germany, September 18-22, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4213},
pages = {91--102},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11871637\_13},
doi = {10.1007/11871637\_13},
timestamp = {Tue, 14 May 2019 10:00:47 +0200},
biburl = {https://dblp.org/rec/conf/pkdd/ChakrabartiA06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-04-11 20:15 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
