Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDAlessandro Lazaric
Person information
- affiliation: Meta AI, France
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[j8]Harsh Satija, Alessandro Lazaric, Matteo Pirotta, Joelle Pineau:
Group Fairness in Reinforcement Learning. Trans. Mach. Learn. Res. 2023 (2023)- [c105]Andrea Tirinzoni, Matteo Pirotta, Alessandro Lazaric:
On the Complexity of Representation Learning in Contextual Linear Bandits. AISTATS 2023: 7871-7896 - [c104]Liyu Chen, Andrea Tirinzoni, Matteo Pirotta, Alessandro Lazaric:
Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path. ALT 2023: 310-357 - [c103]Virginie Do, Elvis Dohmatob, Matteo Pirotta, Alessandro Lazaric, Nicolas Usunier:
Contextual bandits with concave rewards, and an application to fair ranking. ICLR 2023 - [c102]Rui Yuan, Simon Shaolei Du, Robert M. Gower, Alessandro Lazaric, Lin Xiao:
Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies. ICLR 2023 - [c101]Liyu Chen, Andrea Tirinzoni, Alessandro Lazaric, Matteo Pirotta:
Layered State Discovery for Incremental Autonomous Exploration. ICML 2023: 4953-5001 - [i69]Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Alessandro Lazaric, Karteek Alahari:
Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping. CoRR abs/2301.02099 (2023) - [i68]Liyu Chen, Andrea Tirinzoni, Alessandro Lazaric, Matteo Pirotta:
Layered State Discovery for Incremental Autonomous Exploration. CoRR abs/2302.03789 (2023) - 2022
- [j7]Rui Yuan
, Alessandro Lazaric, Robert M. Gower:
Sketched Newton-Raphson. SIAM J. Optim. 32(3): 1555-1583 (2022) - [c100]Rui Yuan, Robert M. Gower, Alessandro Lazaric:
A general sample complexity analysis of vanilla policy gradient. AISTATS 2022: 3332-3380 - [c99]Evrard Garcelon, Vashist Avadhanula, Alessandro Lazaric, Matteo Pirotta:
Top K Ranking for Multi-Armed Bandit with Noisy Evaluations. AISTATS 2022: 6242-6269 - [c98]Jean Tarbouriech, Omar Darwiche Domingues, Pierre Ménard, Matteo Pirotta, Michal Valko, Alessandro Lazaric:
Adaptive Multi-Goal Exploration. AISTATS 2022: 7349-7383 - [c97]Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Alessandro Lazaric, Karteek Alahari:
Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping. CoRL 2022: 1401-1410 - [c96]Pierre-Alexandre Kamienny, Jean Tarbouriech, Sylvain Lamprier, Alessandro Lazaric, Ludovic Denoyer:
Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching. ICLR 2022 - [c95]Yunchang Yang, Tianhao Wu, Han Zhong, Evrard Garcelon, Matteo Pirotta, Alessandro Lazaric, Liwei Wang, Simon Shaolei Du:
A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning. ICLR 2022 - [c94]Denis Yarats, Rob Fergus, Alessandro Lazaric, Lerrel Pinto:
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning. ICLR 2022 - [c93]Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco:
Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times. ICML 2022: 2523-2541 - [c92]Andrea Tirinzoni, Matteo Papini, Ahmed Touati, Alessandro Lazaric, Matteo Pirotta:
Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees. NeurIPS 2022 - [c91]Akram Erraqabi, Marlos C. Machado, Mingde Zhao, Sainbayar Sukhbaatar, Alessandro Lazaric, Ludovic Denoyer, Yoshua Bengio:
Temporal abstractions-augmented temporally contrastive learning: An alternative to the Laplacian in RL. UAI 2022: 641-651 - [i67]Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco:
Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times. CoRR abs/2201.12909 (2022) - [i66]Denis Yarats, David Brandfonbrener, Hao Liu, Michael Laskin, Pieter Abbeel, Alessandro Lazaric, Lerrel Pinto:
Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning. CoRR abs/2201.13425 (2022) - [i65]Akram Erraqabi, Marlos C. Machado, Mingde Zhao, Sainbayar Sukhbaatar, Alessandro Lazaric, Ludovic Denoyer, Yoshua Bengio:
Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL. CoRR abs/2203.11369 (2022) - [i64]Rui Yuan, Simon S. Du, Robert M. Gower, Alessandro Lazaric, Lin Xiao:
Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies. CoRR abs/2210.01400 (2022) - [i63]Liyu Chen, Andrea Tirinzoni, Matteo Pirotta, Alessandro Lazaric:
Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path. CoRR abs/2210.04946 (2022) - [i62]Virginie Do, Elvis Dohmatob, Matteo Pirotta, Alessandro Lazaric, Nicolas Usunier:
Contextual bandits with concave rewards, and an application to fair ranking. CoRR abs/2210.09957 (2022) - [i61]Andrea Tirinzoni, Matteo Papini, Ahmed Touati, Alessandro Lazaric, Matteo Pirotta:
Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees. CoRR abs/2210.13083 (2022) - [i60]Yifang Chen, Karthik Abinav Sankararaman, Alessandro Lazaric, Matteo Pirotta, Dmytro Karamshuk, Qifan Wang, Karishma Mandyam, Sinong Wang, Han Fang:
Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler. CoRR abs/2211.02233 (2022) - [i59]Andrea Tirinzoni, Matteo Pirotta, Alessandro Lazaric:
On the Complexity of Representation Learning in Contextual Linear Bandits. CoRR abs/2212.09429 (2022) - 2021
- [c90]Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric:
Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model. ALT 2021: 1157-1178 - [c89]Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta:
Leveraging Good Representations in Linear Contextual Bandits. ICML 2021: 8371-8380 - [c88]Denis Yarats, Rob Fergus, Alessandro Lazaric, Lerrel Pinto:
Reinforcement Learning with Prototypical Representations. ICML 2021: 11920-11931 - [c87]Jean Tarbouriech, Runlong Zhou, Simon S. Du, Matteo Pirotta, Michal Valko, Alessandro Lazaric:
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret. NeurIPS 2021: 6843-6855 - [c86]Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric:
A Provably Efficient Sample Collection Strategy for Reinforcement Learning. NeurIPS 2021: 7611-7624 - [c85]Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta:
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection. NeurIPS 2021: 16371-16383 - [i58]Denis Yarats, Rob Fergus, Alessandro Lazaric, Lerrel Pinto:
Reinforcement Learning with Prototypical Representations. CoRR abs/2102.11271 (2021) - [i57]Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta:
Leveraging Good Representations in Linear Contextual Bandits. CoRR abs/2104.03781 (2021) - [i56]Jean Tarbouriech, Runlong Zhou, Simon S. Du, Matteo Pirotta, Michal Valko, Alessandro Lazaric:
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret. CoRR abs/2104.11186 (2021) - [i55]Yunchang Yang, Tianhao Wu, Han Zhong, Evrard Garcelon, Matteo Pirotta, Alessandro Lazaric, Liwei Wang, Simon S. Du:
A Unified Framework for Conservative Exploration. CoRR abs/2106.11692 (2021) - [i54]Andrea Tirinzoni, Matteo Pirotta, Alessandro Lazaric:
A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs. CoRR abs/2106.13013 (2021) - [i53]Denis Yarats, Rob Fergus, Alessandro Lazaric, Lerrel Pinto:
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning. CoRR abs/2107.09645 (2021) - [i52]Rui Yuan, Robert M. Gower, Alessandro Lazaric:
A general sample complexity analysis of vanilla policy gradient. CoRR abs/2107.11433 (2021) - [i51]Pierre-Alexandre Kamienny, Jean Tarbouriech, Alessandro Lazaric, Ludovic Denoyer:
Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching. CoRR abs/2110.14457 (2021) - [i50]Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta:
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection. CoRR abs/2110.14798 (2021) - [i49]Jean Tarbouriech, Omar Darwiche Domingues, Pierre Ménard, Matteo Pirotta, Michal Valko, Alessandro Lazaric:
Adaptive Multi-Goal Exploration. CoRR abs/2111.12045 (2021) - [i48]Paul Luyo, Evrard Garcelon, Alessandro Lazaric, Matteo Pirotta:
Differentially Private Exploration in Reinforcement Learning with Linear Representation. CoRR abs/2112.01585 (2021) - [i47]Evrard Garcelon, Vashist Avadhanula, Alessandro Lazaric, Matteo Pirotta:
Top K Ranking for Multi-Armed Bandit with Noisy Evaluations. CoRR abs/2112.06517 (2021) - 2020
- [c84]Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta:
Improved Algorithms for Conservative Exploration in Bandits. AAAI 2020: 3962-3969 - [c83]Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta:
Conservative Exploration in Reinforcement Learning. AISTATS 2020: 1431-1441 - [c82]Andrea Zanette, David Brandfonbrener, Emma Brunskill, Matteo Pirotta, Alessandro Lazaric:
Frequentist Regret Bounds for Randomized Least-Squares Value Iteration. AISTATS 2020: 1954-1964 - [c81]Andrea Tirinzoni, Alessandro Lazaric, Marcello Restelli:
A Novel Confidence-Based Algorithm for Structured Bandits. AISTATS 2020: 3175-3185 - [c80]Julien Seznec, Pierre Ménard, Alessandro Lazaric, Michal Valko:
A single algorithm for both restless and rested rotting bandits. AISTATS 2020: 3784-3794 - [c79]Marc Abeille, Alessandro Lazaric:
Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation. ICML 2020: 23-31 - [c78]Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco:
Near-linear time Gaussian process optimization with adaptive batching and resparsification. ICML 2020: 1295-1305 - [c77]Leonardo Cella, Alessandro Lazaric, Massimiliano Pontil:
Meta-learning with Stochastic Linear Bandits. ICML 2020: 1360-1370 - [c76]Jean Tarbouriech, Evrard Garcelon, Michal Valko, Matteo Pirotta, Alessandro Lazaric:
No-Regret Exploration in Goal-Oriented Reinforcement Learning. ICML 2020: 9428-9437 - [c75]Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill:
Learning Near Optimal Policies with Low Inherent Bellman Error. ICML 2020: 10978-10989 - [c74]Evrard Garcelon, Baptiste Rozière, Laurent Meunier, Jean Tarbouriech, Olivier Teytaud, Alessandro Lazaric, Matteo Pirotta:
Adversarial Attacks on Linear Contextual Bandits. NeurIPS 2020 - [c73]Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric:
Improved Sample Complexity for Incremental Autonomous Exploration in MDPs. NeurIPS 2020 - [c72]Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric:
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits. NeurIPS 2020 - [c71]Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill:
Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration. NeurIPS 2020 - [c70]Jean Tarbouriech, Shubhanshu Shekhar, Matteo Pirotta, Mohammad Ghavamzadeh, Alessandro Lazaric:
Active Model Estimation in Markov Decision Processes. UAI 2020: 1019-1028 - [i46]Jian Qian, Ronan Fruit, Matteo Pirotta, Alessandro Lazaric:
Concentration Inequalities for Multinoulli Random Variables. CoRR abs/2001.11595 (2020) - [i45]Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta:
Conservative Exploration in Reinforcement Learning. CoRR abs/2002.03218 (2020) - [i44]Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta:
Improved Algorithms for Conservative Exploration in Bandits. CoRR abs/2002.03221 (2020) - [i43]Evrard Garcelon, Baptiste Rozière, Laurent Meunier, Jean Tarbouriech, Olivier Teytaud, Alessandro Lazaric, Matteo Pirotta:
Adversarial Attacks on Linear Contextual Bandits. CoRR abs/2002.03839 (2020) - [i42]Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco:
Near-linear Time Gaussian Process Optimization with Adaptive Batching and Resparsification. CoRR abs/2002.09954 (2020) - [i41]Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill:
Learning Near Optimal Policies with Low Inherent Bellman Error. CoRR abs/2003.00153 (2020) - [i40]Jean Tarbouriech, Shubhanshu Shekhar, Matteo Pirotta, Mohammad Ghavamzadeh, Alessandro Lazaric:
Active Model Estimation in Markov Decision Processes. CoRR abs/2003.03297 (2020) - [i39]Pierre-Alexandre Kamienny, Matteo Pirotta, Alessandro Lazaric, Thibault Lavril, Nicolas Usunier, Ludovic Denoyer:
Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization. CoRR abs/2005.02934 (2020) - [i38]Leonardo Cella, Alessandro Lazaric, Massimiliano Pontil:
Meta-learning with Stochastic Linear Bandits. CoRR abs/2005.08531 (2020) - [i37]Andrea Tirinzoni, Alessandro Lazaric, Marcello Restelli:
A Novel Confidence-Based Algorithm for Structured Bandits. CoRR abs/2005.11593 (2020) - [i36]Rui Yuan, Alessandro Lazaric, Robert M. Gower:
Sketched Newton-Raphson. CoRR abs/2006.12120 (2020) - [i35]Ronan Fruit, Matteo Pirotta, Alessandro Lazaric:
Improved Analysis of UCRL2 with Empirical Bernstein Inequality. CoRR abs/2007.05456 (2020) - [i34]Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric:
A Provably Efficient Sample Collection Strategy for Reinforcement Learning. CoRR abs/2007.06437 (2020) - [i33]Marc Abeille, Alessandro Lazaric:
Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation. CoRR abs/2007.06482 (2020) - [i32]Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill:
Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration. CoRR abs/2008.07737 (2020) - [i31]Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric:
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits. CoRR abs/2010.12247 (2020) - [i30]Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric:
Improved Sample Complexity for Incremental Autonomous Exploration in MDPs. CoRR abs/2012.14755 (2020)
2010 – 2019
- 2019
- [c69]Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, Marco Baroni:
Word-order Biases in Deep-agent Emergent Communication. ACL (1) 2019: 5166-5175 - [c68]Jean Tarbouriech, Alessandro Lazaric:
Active Exploration in Markov Decision Processes. AISTATS 2019: 974-982 - [c67]Julien Seznec, Andrea Locatelli, Alexandra Carpentier, Alessandro Lazaric, Michal Valko:
Rotting bandits are no harder than stochastic ones. AISTATS 2019: 2564-2572 - [c66]Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco:
Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret. COLT 2019: 533-557 - [c65]Jian Qian, Ronan Fruit, Matteo Pirotta, Alessandro Lazaric:
Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs. NeurIPS 2019: 4891-4900 - [c64]Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill:
Limiting Extrapolation in Linear Approximate Value Iteration. NeurIPS 2019: 5616-5625 - [c63]Nicolas Carion, Nicolas Usunier, Gabriel Synnaeve, Alessandro Lazaric:
A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning. NeurIPS 2019: 8128-8138 - [c62]Ronald Ortner, Matteo Pirotta, Alessandro Lazaric, Ronan Fruit, Odalric-Ambrym Maillard:
Regret Bounds for Learning State Representations in Reinforcement Learning. NeurIPS 2019: 12717-12727 - [i29]Jean Tarbouriech, Alessandro Lazaric:
Active Exploration in Markov Decision Processes. CoRR abs/1902.11199 (2019) - [i28]Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco:
Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret. CoRR abs/1903.05594 (2019) - [i27]Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, Marco Baroni:
Word-order biases in deep-agent emergent communication. CoRR abs/1905.12330 (2019) - [i26]Nicolas Carion, Gabriel Synnaeve, Alessandro Lazaric, Nicolas Usunier:
A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning. CoRR abs/1910.08809 (2019) - [i25]Andrea Zanette, David Brandfonbrener, Matteo Pirotta, Alessandro Lazaric:
Frequentist Regret Bounds for Randomized Least-Squares Value Iteration. CoRR abs/1911.00567 (2019) - [i24]Jean Tarbouriech, Evrard Garcelon, Michal Valko, Matteo Pirotta, Alessandro Lazaric:
No-Regret Exploration in Goal-Oriented Reinforcement Learning. CoRR abs/1912.03517 (2019) - 2018
- [c61]Marc Abeille, Alessandro Lazaric:
Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems. ICML 2018: 1-9 - [c60]Daniele Calandriello, Ioannis Koutis, Alessandro Lazaric, Michal Valko:
Improved Large-Scale Graph Learning through Ridge Spectral Sparsification. ICML 2018: 687-696 - [c59]Ronan Fruit, Matteo Pirotta, Alessandro Lazaric, Ronald Ortner:
Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning. ICML 2018: 1573-1581 - [c58]Romain Warlop, Alessandro Lazaric, Jérémie Mary:
Fighting Boredom in Recommender Systems with Linear Reinforcement Learning. NeurIPS 2018: 1764-1773 - [c57]Ronan Fruit, Matteo Pirotta, Alessandro Lazaric:
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes. NeurIPS 2018: 2998-3008 - [i23]Ronan Fruit, Matteo Pirotta, Alessandro Lazaric, Ronald Ortner:
Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning. CoRR abs/1802.04020 (2018) - [i22]Daniele Calandriello, Alessandro Lazaric, Michal Valko:
Distributed Adaptive Sampling for Kernel Matrix Approximation. CoRR abs/1803.10172 (2018) - [i21]Ronan Fruit, Matteo Pirotta, Alessandro Lazaric:
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes. CoRR abs/1807.02373 (2018) - [i20]Julien Seznec, Andrea Locatelli, Alexandra Carpentier, Alessandro Lazaric, Michal Valko:
Rotting bandits are no harder than stochastic ones. CoRR abs/1811.11043 (2018) - [i19]Jian Qian, Ronan Fruit, Matteo Pirotta, Alessandro Lazaric:
Exploration Bonus for Regret Minimization in Undiscounted Discrete and Continuous Markov Decision Processes. CoRR abs/1812.04363 (2018) - 2017
- [c56]Romain Warlop, Alessandro Lazaric, Jérémie Mary:
Parallel Higher Order Alternating Least Square for Tensor Recommender System. AAAI Workshops 2017 - [c55]Marc Abeille, Alessandro Lazaric:
Linear Thompson Sampling Revisited. AISTATS 2017: 176-184 - [c54]Ronan Fruit, Alessandro Lazaric:
Exploration-Exploitation in MDPs with Options. AISTATS 2017: 576-584 - [c53]Akram Erraqabi, Alessandro Lazaric, Michal Valko, Emma Brunskill, Yun-En Liu:
Trading off Rewards and Errors in Multi-Armed Bandits. AISTATS 2017: 709-717 - [c52]Marc Abeille, Alessandro Lazaric:
Thompson Sampling for Linear-Quadratic Control Problems. AISTATS 2017: 1246-1254 - [c51]Daniele Calandriello, Alessandro Lazaric, Michal Valko:
Distributed Adaptive Sampling for Kernel Matrix Approximation. AISTATS 2017: 1421-1429 - [c50]Daniele Calandriello, Alessandro Lazaric, Michal Valko:
Second-Order Kernel Online Convex Optimization with Adaptive Sketching. ICML 2017: 645-653 - [c49]Carlos Riquelme, Mohammad Ghavamzadeh, Alessandro Lazaric:
Active Learning for Accurate Estimation of Linear Models. ICML 2017: 2931-2939 - [c48]Ronan Fruit, Matteo Pirotta, Alessandro Lazaric, Emma Brunskill:
Regret Minimization in MDPs with Options without Prior Knowledge. NIPS 2017: 3166-3176 - [c47]Daniele Calandriello, Alessandro Lazaric, Michal Valko:
Efficient Second-Order Online Kernel Learning with Adaptive Embedding. NIPS 2017: 6140-6150 - [i18]Carlos Riquelme, Mohammad Ghavamzadeh, Alessandro Lazaric:
Active Learning for Accurate Estimation of Linear Models. CoRR abs/1703.00579 (2017) - [i17]Ronan Fruit, Alessandro Lazaric:
Exploration-Exploitation in MDPs with Options. CoRR abs/1703.08667 (2017) - [i16]Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar:
Experimental results : Reinforcement Learning of POMDPs using Spectral Methods. CoRR abs/1705.02553 (2017) - [i15]Daniele Calandriello, Alessandro Lazaric, Michal Valko:
Second-Order Kernel Online Convex Optimization with Adaptive Sketching. CoRR abs/1706.04892 (2017) - 2016
- [j6]Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos:
Analysis of Classification-based Policy Iteration Algorithms. J. Mach. Learn. Res. 17: 19:1-19:30 (2016) - [c46]Victor Gabillon, Alessandro Lazaric, Mohammad Ghavamzadeh, Ronald Ortner, Peter L. Bartlett:
Improved Learning Complexity in Combinatorial Pure Exploration Bandits. AISTATS 2016: 1004-1012 - [c45]Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar:
Reinforcement Learning of POMDPs using Spectral Methods. COLT 2016: 193-256 - [c44]Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar:
Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies. COLT 2016: 1639-1642 - [c43]Daniele Calandriello, Alessandro Lazaric, Michal Valko:
Analysis of Nyström method with sequential ridge leverage scores. UAI 2016 - [i14]Daniele Calandriello, Alessandro Lazaric, Michal Valko, Ioannis Koutis:
Incremental Spectral Sparsification for Large-Scale Graph-Based Semi-Supervised Learning. CoRR abs/1601.05675 (2016) - [i13]Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar:
Reinforcement Learning of POMDP's using Spectral Methods. CoRR abs/1602.07764 (2016) - [i12]Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar:
Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies. CoRR abs/1608.04996 (2016) - [i11]Daniele Calandriello, Alessandro Lazaric, Michal Valko:
Analysis of Kelner and Levin graph sparsification algorithm for a streaming setting. CoRR abs/1609.03769 (2016) - [i10]