Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDQuanquan Gu
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[c193]Heyang Zhao, Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu:
Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency. COLT 2023: 4977-5020- [c192]Yuan Cao, Difan Zou, Yuanzhi Li, Quanquan Gu:
The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks. COLT 2023: 5699-5753 - [c191]Zixiang Chen, Chris Junchi Li, Huizhuo Yuan, Quanquan Gu, Michael I. Jordan:
A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning. ICLR 2023 - [c190]Yiwen Kou, Zixiang Chen, Yuan Cao, Quanquan Gu:
How Does Semi-supervised Learning with Pseudo-labelers Work? A Case Study. ICLR 2023 - [c189]Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu:
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization. ICLR 2023 - [c188]Xinzhe Zuo, Zixiang Chen, Huaxiu Yao, Yuan Cao, Quanquan Gu:
Understanding Train-Validation Split in Meta-Learning with Neural Networks. ICLR 2023 - [c187]Qiwei Di, Jiafan He, Dongruo Zhou, Quanquan Gu:
Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path. ICML 2023: 7837-7864 - [c186]Jiaqi Guan, Xiangxin Zhou, Yuwei Yang, Yu Bao, Jian Peng, Jianzhu Ma, Qiang Liu, Liang Wang, Quanquan Gu:
DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design. ICML 2023: 11827-11846 - [c185]Jiafan He, Heyang Zhao, Dongruo Zhou, Quanquan Gu:
Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes. ICML 2023: 12790-12822 - [c184]Yiwen Kou, Zixiang Chen, Yuanzhou Chen, Quanquan Gu:
Benign Overfitting in Two-layer ReLU Convolutional Neural Networks. ICML 2023: 17615-17659 - [c183]Chris Junchi Li, Huizhuo Yuan, Gauthier Gidel, Quanquan Gu, Michael I. Jordan:
Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization. ICML 2023: 20351-20383 - [c182]Yifei Min, Jiafan He, Tianhao Wang, Quanquan Gu:
Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation. ICML 2023: 24785-24811 - [c181]Yue Wu, Shuaicheng Zhang, Wenchao Yu, Yanchi Liu, Quanquan Gu, Dawei Zhou, Haifeng Chen, Wei Cheng:
Personalized Federated Learning under Mixture of Distributions. ICML 2023: 37860-37879 - [c180]Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Sham M. Kakade:
Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron. ICML 2023: 37919-37951 - [c179]Chenlu Ye, Wei Xiong, Quanquan Gu, Tong Zhang:
Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes. ICML 2023: 39834-39863 - [c178]Weitong Zhang, Jiafan He, Zhiyuan Fan, Quanquan Gu:
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits. ICML 2023: 41111-41132 - [c177]Junkai Zhang, Weitong Zhang, Quanquan Gu:
Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs. ICML 2023: 41902-41930 - [c176]Heyang Zhao, Dongruo Zhou, Jiafan He, Quanquan Gu:
Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits. ICML 2023: 42259-42279 - [c175]Zaixiang Zheng, Yifan Deng, Dongyu Xue, Yi Zhou, Fei Ye, Quanquan Gu:
Structure-informed Language Models Are Protein Designers. ICML 2023: 42317-42338 - [c174]Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu:
The Benefits of Mixup for Feature Learning. ICML 2023: 43423-43479 - [c173]Jinghui Chen, Yuan Cao, Quanquan Gu:
Benign Overfitting in Adversarially Robust Linear Classification. UAI 2023: 313-323 - [c172]Lingxiao Wang, Bargav Jayaraman, David Evans, Quanquan Gu:
Efficient Privacy-Preserving Stochastic Nonconvex Optimization. UAI 2023: 2203-2213 - [c171]Yue Wu, Jiafan He, Quanquan Gu:
Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension. UAI 2023: 2304-2313 - [c170]Weitong Zhang, Jiafan He, Dongruo Zhou, Amy Zhang, Quanquan Gu:
Provably efficient representation selection in Low-rank Markov Decision Processes: from online to offline RL. UAI 2023: 2488-2497 - [i118]Zaixiang Zheng, Yifan Deng, Dongyu Xue, Yi Zhou, Fei Ye, Quanquan Gu:
Structure-informed Language Models Are Protein Designers. CoRR abs/2302.01649 (2023) - [i117]Heyang Zhao, Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu:
Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency. CoRR abs/2302.10371 (2023) - [i116]Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Sham M. Kakade:
Learning High-Dimensional Single-Neuron ReLU Networks with Finite Samples. CoRR abs/2303.02255 (2023) - [i115]Yiwen Kou, Zixiang Chen, Yuanzhou Chen, Quanquan Gu:
Benign Overfitting for Two-layer ReLU Networks. CoRR abs/2303.04145 (2023) - [i114]Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu:
The Benefits of Mixup for Feature Learning. CoRR abs/2303.08433 (2023) - [i113]Yue Wu, Tao Jin, Hao Lou, Farzad Farnoud, Quanquan Gu:
Borda Regret Minimization for Generalized Linear Dueling Bandits. CoRR abs/2303.08816 (2023) - [i112]Weitong Zhang, Jiafan He, Zhiyuan Fan, Quanquan Gu:
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits. CoRR abs/2303.09390 (2023) - [i111]Junkai Zhang, Weitong Zhang, Quanquan Gu:
Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs. CoRR abs/2303.10165 (2023) - [i110]Yue Wu, Shuaicheng Zhang, Wenchao Yu, Yanchi Liu, Quanquan Gu, Dawei Zhou, Haifeng Chen, Wei Cheng:
Personalized Federated Learning under Mixture of Distributions. CoRR abs/2305.01068 (2023) - [i109]Yifei Min, Jiafan He, Tianhao Wang, Quanquan Gu:
Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation. CoRR abs/2305.06446 (2023) - [i108]Yue Wu, Jiafan He, Quanquan Gu:
Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension. CoRR abs/2305.08350 (2023) - [i107]Kaixuan Ji, Qingyue Zhao, Jiafan He, Weitong Zhang, Quanquan Gu:
Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs. CoRR abs/2305.08359 (2023) - [i106]Chen Ling, Xujiang Zhao, Jiaying Lu, Chengyuan Deng, Can Zheng, Junxiang Wang, Tanmoy Chowdhury, Yun Li, Hejie Cui, Xuchao Zhang, Tianjiao Zhao, Amit Panalkar, Wei Cheng, Haoyu Wang, Yanchi Liu, Zhengzhang Chen, Haifeng Chen, Chris White, Quanquan Gu, Carl Yang, Liang Zhao:
Beyond One-Model-Fits-All: A Survey of Domain Specialization for Large Language Models. CoRR abs/2305.18703 (2023) - [i105]Yihe Deng, Yu Yang, Baharan Mirzasoleiman, Quanquan Gu:
Robust Learning with Progressive Data Expansion Against Spurious Correlation. CoRR abs/2306.04949 (2023) - [i104]Yuan Cao, Difan Zou, Yuanzhi Li, Quanquan Gu:
The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks. CoRR abs/2306.11680 (2023) - [i103]Jiasheng Ye, Zaixiang Zheng, Yu Bao, Lihua Qian, Quanquan Gu:
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning. CoRR abs/2308.12219 (2023) - 2022
- [c169]Jinghui Chen, Yu Cheng, Zhe Gan, Quanquan Gu, Jingjing Liu:
Efficient Robust Training via Backward Smoothing. AAAI 2022: 6222-6230 - [c168]Chonghua Liao, Jiafan He, Quanquan Gu:
Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes. ACML 2022: 627-642 - [c167]Yue Wu, Dongruo Zhou, Quanquan Gu:
Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation. AISTATS 2022: 3883-3913 - [c166]Jiafan He, Dongruo Zhou, Quanquan Gu:
Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs. AISTATS 2022: 4259-4280 - [c165]Spencer Frei, Difan Zou, Zixiang Chen, Quanquan Gu:
Self-training Converts Weak Learners to Strong Learners in Mixture Models. AISTATS 2022: 8003-8021 - [c164]Yue Wu, Tao Jin, Hao Lou, Pan Xu, Farzad Farnoud, Quanquan Gu:
Adaptive Sampling for Heterogeneous Rank Aggregation from Noisy Pairwise Comparisons. AISTATS 2022: 11014-11036 - [c163]Zixiang Chen, Dongruo Zhou, Quanquan Gu:
Faster Perturbed Stochastic Gradient Methods for Finding Local Minima. ALT 2022: 176-204 - [c162]Zixiang Chen, Dongruo Zhou, Quanquan Gu:
Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games. ALT 2022: 227-261 - [c161]Zhe Wu, Aisha Alnajdi, Quanquan Gu, Panagiotis D. Christofides:
Machine-Learning-based Predictive Control of Nonlinear Processes with Uncertainty. ACC 2022: 2810-2816 - [c160]Pan Xu, Zheng Wen, Handong Zhao, Quanquan Gu:
Neural Contextual Bandits with Deep Representation and Shallow Exploration. ICLR 2022 - [c159]Yiling Jia, Weitong Zhang, Dongruo Zhou, Quanquan Gu, Hongning Wang:
Learning Neural Contextual Bandits through Perturbed Rewards. ICLR 2022 - [c158]Yihan Wang, Zhouxing Shi, Quanquan Gu, Cho-Jui Hsieh:
On the Convergence of Certified Robust Training with Interval Bound Propagation. ICLR 2022 - [c157]Yuanzhou Chen, Jiafan He, Quanquan Gu:
On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs. ICML 2022: 3149-3183 - [c156]Yifei Min, Jiafan He, Tianhao Wang, Quanquan Gu:
Learning Stochastic Shortest Path with Linear Function Approximation. ICML 2022: 15584-15629 - [c155]Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade:
Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression. ICML 2022: 24280-24314 - [c154]Dongruo Zhou, Quanquan Gu:
Dimension-free Complexity Bounds for High-order Nonconvex Finite-sum Optimization. ICML 2022: 27143-27158 - [c153]Yuan Cao, Zixiang Chen, Misha Belkin, Quanquan Gu:
Benign Overfitting in Two-layer Convolutional Neural Networks. NeurIPS 2022 - [c152]Zixiang Chen, Yihe Deng, Yue Wu, Quanquan Gu, Yuanzhi Li:
Towards Understanding the Mixture-of-Experts Layer in Deep Learning. NeurIPS 2022 - [c151]Jiafan He, Tianhao Wang, Yifei Min, Quanquan Gu:
A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits. NeurIPS 2022 - [c150]Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu:
Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions. NeurIPS 2022 - [c149]Chris Junchi Li, Dongruo Zhou, Quanquan Gu, Michael I. Jordan:
Learning Two-Player Markov Games: Neural Function Approximation and Correlated Equilibrium. NeurIPS 2022 - [c148]Hao Lou, Tao Jin, Yue Wu, Pan Xu, Quanquan Gu, Farzad Farnoud:
Active Ranking without Strong Stochastic Transitivity. NeurIPS 2022 - [c147]Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade:
The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift. NeurIPS 2022 - [c146]Dongruo Zhou, Quanquan Gu:
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs. NeurIPS 2022 - [c145]Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade:
Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime. NeurIPS 2022 - [i102]Yiling Jia, Weitong Zhang, Dongruo Zhou, Quanquan Gu, Hongning Wang:
Learning Contextual Bandits Through Perturbed Rewards. CoRR abs/2201.09910 (2022) - [i101]Yuan Cao, Zixiang Chen, Mikhail Belkin, Quanquan Gu:
Benign Overfitting in Two-layer Convolutional Neural Networks. CoRR abs/2202.06526 (2022) - [i100]Heyang Zhao, Dongruo Zhou, Jiafan He, Quanquan Gu:
Bandit Learning with General Function Classes: Heteroscedastic Noise and Variance-dependent Regret Bounds. CoRR abs/2202.13603 (2022) - [i99]Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade:
Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime. CoRR abs/2203.03159 (2022) - [i98]Yihan Wang, Zhouxing Shi, Quanquan Gu, Cho-Jui Hsieh:
On the Convergence of Certified Robust Training with Interval Bound Propagation. CoRR abs/2203.08961 (2022) - [i97]Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu:
Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions. CoRR abs/2205.06811 (2022) - [i96]Dongruo Zhou, Quanquan Gu:
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs. CoRR abs/2205.11507 (2022) - [i95]Jiafan He, Tianhao Wang, Yifei Min, Quanquan Gu:
A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits. CoRR abs/2207.03106 (2022) - [i94]Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade:
The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift. CoRR abs/2208.01857 (2022) - [i93]Zixiang Chen, Yihe Deng, Yue Wu, Quanquan Gu, Yuanzhi Li:
Towards Understanding Mixture of Experts in Deep Learning. CoRR abs/2208.02813 (2022) - [i92]Chris Junchi Li, Dongruo Zhou, Quanquan Gu, Michael I. Jordan:
Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium. CoRR abs/2208.05363 (2022) - [i91]Zixiang Chen, Chris Junchi Li, Angela Yuan, Quanquan Gu, Michael I. Jordan:
A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning. CoRR abs/2209.15634 (2022) - [i90]Chenlu Ye, Wei Xiong, Quanquan Gu, Tong Zhang:
Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes. CoRR abs/2212.05949 (2022) - [i89]Jiafan He, Heyang Zhao, Dongruo Zhou, Quanquan Gu:
Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes. CoRR abs/2212.06132 (2022) - 2021
- [j9]Bargav Jayaraman, Lingxiao Wang, Katherine Knipmeyer, Quanquan Gu, David Evans:
Revisiting Membership Inference Under Realistic Assumptions. Proc. Priv. Enhancing Technol. 2021(2): 348-368 (2021) - [j8]Bao Wang
, Difan Zou, Quanquan Gu, Stanley J. Osher:
Laplacian Smoothing Stochastic Gradient Markov Chain Monte Carlo. SIAM J. Sci. Comput. 43(1): A26-A53 (2021) - [c144]Tianyuan Jin, Pan Xu, Xiaokui Xiao, Quanquan Gu:
Double Explore-then-Commit: Asymptotic Optimality and Beyond. COLT 2021: 2584-2633 - [c143]Dongruo Zhou, Quanquan Gu, Csaba Szepesvári:
Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes. COLT 2021: 4532-4576 - [c142]Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade:
Benign Overfitting of Constant-Stepsize SGD for Linear Regression. COLT 2021: 4633-4635 - [c141]Zixiang Chen, Yuan Cao, Difan Zou, Quanquan Gu:
How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks? ICLR 2021 - [c140]Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu:
Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate. ICLR 2021 - [c139]Weitong Zhang, Dongruo Zhou, Lihong Li, Quanquan Gu:
Neural Thompson Sampling. ICLR 2021 - [c138]Spencer Frei, Yuan Cao, Quanquan Gu:
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins. ICML 2021: 3417-3426 - [c137]Spencer Frei, Yuan Cao, Quanquan Gu:
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise. ICML 2021: 3427-3438 - [c136]Jiafan He, Dongruo Zhou, Quanquan Gu:
Logarithmic Regret for Reinforcement Learning with Linear Function Approximation. ICML 2021: 4171-4180 - [c135]Tianyuan Jin, Jing Tang, Pan Xu, Keke Huang, Xiaokui Xiao, Quanquan Gu:
Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits. ICML 2021: 5065-5073 - [c134]Tianyuan Jin, Pan Xu, Jieming Shi, Xiaokui Xiao, Quanquan Gu:
MOTS: Minimax Optimal Thompson Sampling. ICML 2021: 5074-5083 - [c133]Dongruo Zhou, Jiafan He, Quanquan Gu:
Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping. ICML 2021: 12793-12802 - [c132]Difan Zou, Spencer Frei, Quanquan Gu:
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise. ICML 2021: 13002-13011 - [c131]Difan Zou, Quanquan Gu:
On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients. ICML 2021: 13012-13022 - [c130]Yuan Cao, Zhiying Fang, Yue Wu, Ding-Xuan Zhou, Quanquan Gu:
Towards Understanding the Spectral Bias of Deep Learning. IJCAI 2021: 2205-2211 - [c129]Lingxiao Wang, Kevin Huang, Tengyu Ma, Quanquan Gu, Jing Huang:
Variance-reduced First-order Meta-learning for Natural Language Processing Tasks. NAACL-HLT 2021: 2609-2615 - [c128]Weitong Zhang, Dongruo Zhou, Quanquan Gu:
Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation. NeurIPS 2021: 1582-1593 - [c127]Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Dean P. Foster, Sham M. Kakade:
The Benefits of Implicit Regularization from SGD in Least Squares Problems. NeurIPS 2021: 5456-5468 - [c126]Hanxun Huang, Yisen Wang, Sarah M. Erfani, Quanquan Gu, James Bailey, Xingjun Ma:
Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks. NeurIPS 2021: 5545-5559 - [c125]Boxi Wu, Jinghui Chen, Deng Cai, Xiaofei He, Quanquan Gu:
Do Wider Neural Networks Really Help Adversarial Robustness? NeurIPS 2021: 7054-7067 - [c124]Yifei Min, Tianhao Wang, Dongruo Zhou, Quanquan Gu:
Variance-Aware Off-Policy Evaluation with Linear Function Approximation. NeurIPS 2021: 7598-7610 - [c123]Spencer Frei, Quanquan Gu:
Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent. NeurIPS 2021: 7937-7949 - [c122]Yuan Cao, Quanquan Gu, Mikhail Belkin:
Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures. NeurIPS 2021: 8407-8418 - [c121]Yinglun Zhu, Dongruo Zhou, Ruoxi Jiang, Quanquan Gu, Rebecca Willett, Robert Nowak:
Pure Exploration in Kernel and Neural Bandits. NeurIPS 2021: 11618-11630 - [c120]Tianhao Wang, Dongruo Zhou, Quanquan Gu:
Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints. NeurIPS 2021: 13524-13536 - [c119]Jiafan He, Dongruo Zhou, Quanquan Gu:
Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation. NeurIPS 2021: 14188-14199 - [c118]Jiafan He, Dongruo Zhou, Quanquan Gu:
Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs. NeurIPS 2021: 22288-22300 - [c117]Luyao Yuan, Dongruo Zhou, Junhong Shen, Jingdong Gao, Jeffrey L. Chen, Quanquan Gu, Ying Nian Wu, Song-Chun Zhu:
Iterative Teacher-Aware Learning. NeurIPS 2021: 29231-29245 - [c116]Difan Zou, Pan Xu, Quanquan Gu:
Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave Sampling. UAI 2021: 1152-1162 - [i88]Spencer Frei, Yuan Cao, Quanquan Gu:
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise. CoRR abs/2101.01152 (2021) - [i87]Tianhao Wang, Dongruo Zhou, Quanquan Gu:
Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints. CoRR abs/2101.02195 (2021) - [i86]Yue Wu, Dongruo Zhou, Quanquan Gu:
Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation. CoRR abs/2102.07301 (2021) - [i85]Zixiang Chen, Dongruo Zhou, Quanquan Gu:
Almost Optimal Algorithms for Two-player Markov Games with Linear Function Approximation. CoRR abs/2102.07404 (2021) - [i84]Jiafan He, Dongruo Zhou, Quanquan Gu:
Nearly Optimal Regret for Learning Adversarial MDPs with Linear Function Approximation. CoRR abs/2102.08940 (2021) - [i83]Quanquan Gu, Amin Karbasi, Khashayar Khosravi, Vahab S. Mirrokni, Dongruo Zhou:
Batched Neural Bandits. CoRR abs/2102.13028 (2021) - [i82]Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade:
Benign Overfitting of Constant-Stepsize SGD for Linear Regression. CoRR abs/2103.12692 (2021) - [i81]Difan Zou, Spencer Frei, Quanquan Gu:
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise. CoRR abs/2104.09437 (2021) - [i80]Yuan Cao, Quanquan Gu, Mikhail Belkin:
Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures. CoRR abs/2104.13628 (2021) - [i79]Jiafan He, Dongruo Zhou, Quanquan Gu:
Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation. CoRR abs/2106.11612 (2021) - [i78]Weitong Zhang, Jiafan He, Dongruo Zhou, Amy Zhang, Quanquan Gu:
Provably Efficient Representation Learning in Low-rank Markov Decision Processes. CoRR abs/2106.11935 (2021) - [i77]Yifei Min, Tianhao Wang, Dongruo Zhou, Quanquan Gu:
Variance-Aware Off-Policy Evaluation with Linear Function Approximation. CoRR abs/2106.11960 (2021) - [i76]Yinglun Zhu, Dongruo Zhou, Ruoxi Jiang, Quanquan Gu, Rebecca Willett, Robert D. Nowak:
Pure Exploration in Kernel and Neural Bandits. CoRR abs/2106.12034 (2021) - [i75]Spencer Frei, Quanquan Gu:
Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent. CoRR abs/2106.13792 (2021) - [i74]Spencer Frei, Difan Zou, Zixiang Chen, Quanquan Gu:
Self-training Converts Weak Learners to Strong Learners in Mixture Models. CoRR abs/2106.13805 (2021) - [i73]Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Dean P. Foster, Sham M. Kakade:
The Benefits of Implicit Regularization from SGD in Least Squares Problems. CoRR abs/2108.04552 (2021) - [i72]