Simon S. Du - RankMe

226 papers A* 69A 8B 1Journal 138Unranked 9

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation. CoRR Tiantian Wang, Xiang Xiang, Simon S. Du
2026	J	`jnl`	Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning. CoRR Zhiwen You, Xi Chen, Aniket Vashishtha, Simon S. Du, Gabriel Erion-Barner, Hongyuan Mei, Hao Peng, Yue Guo
2025	J	`jnl`	A Minimalist Example of Edge-of-Stability and Progressive Sharpening. CoRR Liming Liu, Zixuan Zhang, Simon S. Du, Tuo Zhao
2025	A*	`conf`	Anytime Acceleration of Gradient Descent. COLT Zihan Zhang, Jason D. Lee, Simon S. Du, Yuxin Chen
2025	B	`conf`	Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination. CogSci Kunal Jha, Wilka Carvalho, Yancheng Liang, Simon S. Du, Natasha Jaques, Max Kleiman-Weiner
2025	J	`jnl`	Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination. CoRR Kunal Jha, Wilka Carvalho, Yancheng Liang, Simon S. Du, Max Kleiman-Weiner, Natasha Jaques
2025	J	`jnl`	Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback. CoRR Runlong Zhou, Maryam Fazel, Simon S. Du
2025	J	`jnl`	Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures. CoRR Mo Zhou, Weihang Xu, Maryam Fazel, Simon S. Du
2025	J	`jnl`	Improving Human-AI Coordination through Adversarial Training and Generative Models. CoRR Paresh Chaudhary, Yancheng Liang, Daphne Chen, Simon S. Du, Natasha Jaques
2025	J	`jnl`	Optimal Multi-Distribution Learning. J. ACM Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
2025	J	`jnl`	Settling the Sample Complexity of Online Reinforcement Learning. J. ACM Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du
2025	J	`jnl`	Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs. CoRR Shulun Chen, Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du
2025	J	`jnl`	Towards Understanding the Benefit of Multitask Representation Learning in Decision Process. CoRR Rui Lu, Yang Yue, Andrew Zhao, Simon S. Du, Gao Huang
2025	J	`jnl`	Understanding the Gain from Data Filtering in Multimodal Contrastive Learning. CoRR Divyansh Pareek, Sewoong Oh, Simon S. Du
2025	J	`jnl`	Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO. CoRR Ruizhe Shi, Minhak Song, Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du
2025	J	`jnl`	Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback. CoRR Shulun Chen, Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du
2024	—	`conf`	An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models. ACL (Findings) Gantavya Bhatt, Yifang Chen, Arnav Mohanty Das, Jifan Zhang, Sang T. Truong, Stephen Mussmann, Yinglun Zhu, Jeff A. Bilmes, Simon S. Du, Kevin Jamieson, Jordan T. Ash, Robert D. Nowak
2024	J	`jnl`	An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models. CoRR Gantavya Bhatt, Yifang Chen, Arnav Mohanty Das, Jifan Zhang, Sang T. Truong, Stephen Mussmann, Yinglun Zhu, Jeffrey A. Bilmes, Simon S. Du, Kevin Jamieson, Jordan T. Ash, Robert D. Nowak
2024	J	`jnl`	Anytime Acceleration of Gradient Descent. CoRR Zihan Zhang, Jason D. Lee, Simon S. Du, Yuxin Chen
2024	A*	`conf`	CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning. NeurIPS Yiping Wang, Yifang Chen, Wendan Yan, Alex Fang, Wenjing Zhou, Kevin Jamieson, Simon S. Du
2024	A*	`conf`	Decoding-Time Language Model Alignment with Multiple Objectives. NeurIPS Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hanna Hajishirzi, Noah A. Smith, Simon S. Du
2024	J	`jnl`	Decoding-Time Language Model Alignment with Multiple Objectives. CoRR Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hannaneh Hajishirzi, Noah A. Smith, Simon S. Du
2024	A*	`conf`	Distributional Successor Features Enable Zero-Shot Policy Optimization. NeurIPS Chuning Zhu, Xinqi Wang, Tyler Han, Simon S. Du, Abhishek Gupta
2024	J	`jnl`	Horizon-Free Regret for Linear Markov Decision Processes. CoRR Zihan Zhang, Jason D. Lee, Yuxin Chen, Simon S. Du
2024	A*	`conf`	Learning Optimal Tax Design in Nonatomic Congestion Games. NeurIPS Qiwen Cui, Maryam Fazel, Simon S. Du
2024	J	`jnl`	Learning Optimal Tax Design in Nonatomic Congestion Games. CoRR Qiwen Cui, Maryam Fazel, Simon S. Du
2024	A*	`conf`	Learning to Cooperate with Humans using Generative Agents. NeurIPS Yancheng Liang, Daphne Chen, Abhishek Gupta, Simon S. Du, Natasha Jaques
2024	J	`jnl`	Learning to Cooperate with Humans using Generative Agents. CoRR Yancheng Liang, Daphne Chen, Abhishek Gupta, Simon S. Du, Natasha Jaques
2024	J	`jnl`	Multi-Agent Reinforcement Learning from Human Feedback: Data Coverage and Algorithmic Techniques. CoRR Natalia Zhang, Xinqi Wang, Qiwen Cui, Runlong Zhou, Sham M. Kakade, Simon S. Du
2024	A*	`conf`	Optimal Multi-Distribution Learning. COLT Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
2024	A*	`conf`	Refined Sample Complexity for Markov Games with Independent Linear Function Approximation (Extended Abstract). COLT Yan Dai, Qiwen Cui, Simon S. Du
2024	J	`jnl`	Refined Sample Complexity for Markov Games with Independent Linear Function Approximation. CoRR Yan Dai, Qiwen Cui, Simon S. Du
2024	—	`conf`	Reflect-RL: Two-Player Online RL Fine-Tuning for LMs. ACL (1) Runlong Zhou, Simon S. Du, Beibin Li
2024	J	`jnl`	Reflect-RL: Two-Player Online RL Fine-Tuning for LMs. CoRR Runlong Zhou, Simon S. Du, Beibin Li
2024	J	`jnl`	Rethinking Transformers in Solving POMDPs. CoRR Chenhao Lu, Ruizhe Shi, Yuyao Liu, Kaizhe Hu, Simon S. Du, Huazhe Xu
2024	A*	`conf`	Settling the sample complexity of online reinforcement learning. COLT Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du
2024	J	`jnl`	The Crucial Role of Samplers in Online Direct Preference Optimization. CoRR Ruizhe Shi, Runlong Zhou, Simon S. Du
2024	J	`jnl`	Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models. CoRR Weihang Xu, Maryam Fazel, Simon S. Du
2024	A*	`conf`	Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models. NeurIPS Weihang Xu, Maryam Fazel, Simon S. Du
2024	J	`jnl`	Transferable Reinforcement Learning via Generalized Occupancy Models. CoRR Chuning Zhu, Xinqi Wang, Tyler Han, Simon S. Du, Abhishek Gupta
2024	A*	`conf`	Understanding the Gains from Repeated Self-Distillation. NeurIPS Divyansh Pareek, Simon S. Du, Sewoong Oh
2024	J	`jnl`	Understanding the Gains from Repeated Self-Distillation. CoRR Divyansh Pareek, Simon S. Du, Sewoong Oh
2023	J	`jnl`	A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning. CoRR Haozhe Jiang, Qiwen Cui, Zhihan Xiong, Maryam Fazel, Simon S. Du
2023	A*	`conf`	A Reduction-based Framework for Sequential Decision Making with Delayed Feedback. NeurIPS Yunchang Yang, Han Zhong, Tianhao Wu, Bin Liu, Liwei Wang, Simon S. Du
2023	J	`jnl`	A Reduction-based Framework for Sequential Decision Making with Delayed Feedback. CoRR Yunchang Yang, Han Zhong, Tianhao Wu, Bin Liu, Liwei Wang, Simon S. Du
2023	J	`jnl`	Active Representation Learning for General Task Space with Applications in Robotics. CoRR Yifang Chen, Yingbing Huang, Simon S. Du, Kevin Jamieson, Guanya Shi
2023	A*	`conf`	Active representation learning for general task space with applications in robotics. NeurIPS Yifang Chen, Yingbing Huang, Simon S. Du, Kevin Jamieson, Guanya Shi
2023	A	`conf`	Blessing of Class Diversity in Pre-training. AISTATS Yulai Zhao, Jianshu Chen, Simon S. Du
2023	A*	`conf`	Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation. COLT Qiwen Cui, Kaiqing Zhang, Simon S. Du
2023	J	`jnl`	Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation. CoRR Qiwen Cui, Kaiqing Zhang, Simon S. Du
2023	J	`jnl`	Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking. CoRR Kaifeng Lyu, Jikai Jin, Zhiyuan Li, Simon S. Du, Jason D. Lee, Wei Hu
2023	J	`jnl`	How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization. CoRR Nuoya Xiong, Lijun Ding, Simon S. Du
2023	J	`jnl`	Improved Active Multi-Task Representation Learning via Lasso. CoRR Yiping Wang, Yifang Chen, Kevin Jamieson, Simon S. Du
2023	J	`jnl`	JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention. CoRR Yuandong Tian, Yiping Wang, Zhenyu Zhang, Beidi Chen, Simon S. Du
2023	A*	`conf`	Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure. NeurIPS Angela Yuan, Chris Junchi Li, Gauthier Gidel, Michael I. Jordan, Quanquan Gu, Simon S. Du
2023	J	`jnl`	Optimal Multi-Distribution Learning. CoRR Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
2023	A*	`conf`	Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron. COLT Weihang Xu, Simon S. Du
2023	J	`jnl`	Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron. CoRR Weihang Xu, Simon S. Du
2023	A*	`conf`	Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer. NeurIPS Yuandong Tian, Yiping Wang, Beidi Chen, Simon S. Du
2023	J	`jnl`	Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer. CoRR Yuandong Tian, Yiping Wang, Beidi Chen, Simon S. Du
2023	J	`jnl`	Settling the Sample Complexity of Online Reinforcement Learning. CoRR Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du
2023	J	`jnl`	Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments. CoRR Runlong Zhou, Zihan Zhang, Simon S. Du
2023	J	`jnl`	Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing. CoRR Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon S. Du, Jason D. Lee
2023	J	`jnl`	Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning. CoRR Ruizhe Shi, Yuyao Liu, Yanjie Ze, Simon S. Du, Huazhe Xu
2022	A*	`conf`	Active Multi-Task Representation Learning. ICML Yifang Chen, Kevin Jamieson, Simon S. Du
2022	J	`jnl`	Active Multi-Task Representation Learning. CoRR Yifang Chen, Simon S. Du, Kevin Jamieson
2022	J	`jnl`	Blessing of Class Diversity in Pre-training. CoRR Yulai Zhao, Jianshu Chen, Simon S. Du
2022	A*	`conf`	Denoised MDPs: Learning World Models Better Than the World Itself. ICML Tongzhou Wang, Simon S. Du, Antonio Torralba, Phillip Isola, Amy Zhang, Yuandong Tian
2022	J	`jnl`	Denoised MDPs: Learning World Models Better Than the World Itself. CoRR Tongzhou Wang, Simon S. Du, Antonio Torralba, Phillip Isola, Amy Zhang, Yuandong Tian
2022	J	`jnl`	Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games. CoRR Shicong Cen, Yuejie Chi, Simon S. Du, Lin Xiao
2022	A*	`conf`	First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach. ICML Andrew J. Wagenmaker, Yifang Chen, Max Simchowitz, Simon S. Du, Kevin Jamieson
2022	A	`conf`	Gap-Dependent Bounds for Two-Player Markov Games. AISTATS Zehao Dou, Zhuoran Yang, Zhaoran Wang, Simon S. Du
2022	J	`jnl`	Horizon-Free Reinforcement Learning for Latent Markov Decision Processes. CoRR Runlong Zhou, Ruosong Wang, Simon S. Du
2022	A*	`conf`	Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies. COLT Zihan Zhang, Xiangyang Ji, Simon S. Du
2022	J	`jnl`	Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies. CoRR Zihan Zhang, Xiangyang Ji, Simon S. Du
2022	A*	`conf`	Learning in Congestion Games with Bandit Feedback. NeurIPS Qiwen Cui, Zhihan Xiong, Maryam Fazel, Simon S. Du
2022	J	`jnl`	Learning in Congestion Games with Bandit Feedback. CoRR Qiwen Cui, Zhihan Xiong, Maryam Fazel, Simon S. Du
2022	J	`jnl`	Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies. CoRR Rui Yuan, Simon S. Du, Robert M. Gower, Alessandro Lazaric, Lin Xiao
2022	A*	`conf`	Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path. ICML Haoyuan Cai, Tengyu Ma, Simon S. Du
2022	J	`jnl`	Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path. CoRR Haoyuan Cai, Tengyu Ma, Simon S. Du
2022	A*	`conf`	Near-Optimal Randomized Exploration for Tabular Markov Decision Processes. NeurIPS Zhihan Xiong, Ruoqi Shen, Qiwen Cui, Maryam Fazel, Simon S. Du
2022	J	`jnl`	Nearly Minimax Algorithms for Linear Bandits with Shared Representation. CoRR Jiaqi Yang, Qi Lei, Jason D. Lee, Simon S. Du
2022	A*	`conf`	Nearly Optimal Policy Optimization with Stable at Any Time Guarantee. ICML Tianhao Wu, Yunchang Yang, Han Zhong, Liwei Wang, Simon S. Du, Jiantao Jiao
2022	J	`jnl`	Offline congestion games: How feedback type affects data coverage requirement. CoRR Haozhe Jiang, Qiwen Cui, Zhihan Xiong, Maryam Fazel, Simon S. Du
2022	A*	`conf`	On Gap-dependent Bounds for Offline Reinforcement Learning. NeurIPS Xinqi Wang, Qiwen Cui, Simon S. Du
2022	J	`jnl`	On Gap-dependent Bounds for Offline Reinforcement Learning. CoRR Xinqi Wang, Qiwen Cui, Simon S. Du
2022	J	`jnl`	On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness. CoRR Haotian Ye, Xiaoyu Chen, Liwei Wang, Simon S. Du
2022	J	`jnl`	Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization. CoRR Simon S. Du, Gauthier Gidel, Michael I. Jordan, Chris Junchi Li
2022	A*	`conf`	Provable General Function Class Representation Learning in Multitask Bandits and MDP. NeurIPS Rui Lu, Andrew Zhao, Simon S. Du, Gao Huang
2022	J	`jnl`	Provable General Function Class Representation Learning in Multitask Bandits and MDPs. CoRR Rui Lu, Andrew Zhao, Simon S. Du, Gao Huang
2022	A*	`conf`	Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus. NeurIPS Qiwen Cui, Simon S. Du
2022	J	`jnl`	Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus. CoRR Qiwen Cui, Simon S. Du
2022	A	`conf`	Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games. AISTATS Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du
2022	A*	`conf`	Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes. ICML Andrew J. Wagenmaker, Yifang Chen, Max Simchowitz, Simon S. Du, Kevin Jamieson
2022	J	`jnl`	Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes. CoRR Andrew Wagenmaker, Yifang Chen, Max Simchowitz, Simon S. Du, Kevin Jamieson
2022	J	`jnl`	TransFollower: Long-Sequence Car-Following Trajectory Prediction through Transformer. CoRR Meixin Zhu, Simon S. Du, Xuesong Wang, Hao (Frank) Yang, Ziyuan Pu, Yinhai Wang
2022	J	`jnl`	Understanding Curriculum Learning in Policy Optimization for Solving Combinatorial Optimization Problems. CoRR Runlong Zhou, Yuandong Tian, Yi Wu, Simon S. Du
2022	J	`jnl`	Understanding the acceleration phenomenon via high-resolution differential equations. Math. Program. Bin Shi, Simon S. Du, Michael I. Jordan, Weijie J. Su
2022	J	`jnl`	Variance-Aware Sparse Linear Bandits. CoRR Yan Dai, Ruosong Wang, Simon S. Du
2022	A*	`conf`	When are Offline Two-Player Zero-Sum Markov Games Solvable? NeurIPS Qiwen Cui, Simon S. Du
2022	J	`jnl`	When is Offline Two-Player Zero-Sum Markov Game Solvable? CoRR Qiwen Cui, Simon S. Du
2021	J	`jnl`	A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost. CoRR Minbo Gao, Tianle Xie, Simon S. Du, Lin F. Yang
2021	J	`jnl`	A Unified Framework for Conservative Exploration. CoRR Yunchang Yang, Tianhao Wu, Han Zhong, Evrard Garcelon, Matteo Pirotta, Alessandro Lazaric, Liwei Wang, Simon S. Du
2021	J	`jnl`	AdaLoss: A computationally-efficient and provably convergent adaptive gradient method. CoRR Xiaoxia Wu, Yuege Xie, Simon S. Du, Rachel A. Ward
2021	A*	`conf`	Bilinear Classes: A Structural Framework for Provable Generalization in RL. ICML Simon S. Du, Sham M. Kakade, Jason D. Lee, Shachar Lovett, Gaurav Mahajan, Wen Sun, Ruosong Wang
2021	J	`jnl`	Bilinear Classes: A Structural Framework for Provable Generalization in RL. CoRR Simon S. Du, Sham M. Kakade, Jason D. Lee, Shachar Lovett, Gaurav Mahajan, Wen Sun, Ruosong Wang
2021	A*	`conf`	Corruption Robust Active Learning. NeurIPS Yifang Chen, Simon S. Du, Kevin Jamieson
2021	J	`jnl`	Corruption Robust Active Learning. CoRR Yifang Chen, Simon S. Du, Kevin Jamieson
2021	J	`jnl`	Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization. CoRR Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon S. Du, Yu Wang, Yi Wu
2021	A*	`conf`	Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap. COLT Haike Xu, Tengyu Ma, Simon S. Du
2021	J	`jnl`	Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap. CoRR Haike Xu, Tengyu Ma, Simon S. Du
2021	J	`jnl`	First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach. CoRR Andrew Wagenmaker, Yifang Chen, Max Simchowitz, Simon S. Du, Kevin Jamieson
2021	J	`jnl`	Gap-Dependent Bounds for Two-Player Markov Games. CoRR Zehao Dou, Zhuoran Yang, Zhaoran Wang, Simon S. Du
2021	A*	`conf`	Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization. NeurIPS Tian Ye, Simon S. Du
2021	J	`jnl`	Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization. CoRR Tian Ye, Simon S. Du
2021	A*	`conf`	Improved Corruption Robust Algorithms for Episodic Reinforcement Learning. ICML Yifang Chen, Simon S. Du, Kevin Jamieson
2021	J	`jnl`	Improved Corruption Robust Algorithms for Episodic Reinforcement Learning. CoRR Yifang Chen, Simon S. Du, Kevin Jamieson
2021	A*	`conf`	Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP. NeurIPS Zihan Zhang, Jiaqi Yang, Xiangyang Ji, Simon S. Du
2021	A*	`conf`	Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon. COLT Zihan Zhang, Xiangyang Ji, Simon S. Du
2021	A*	`conf`	Near Optimal Reward-Free Reinforcement Learning. ICML Zihan Zhang, Simon S. Du, Xiangyang Ji
2021	J	`jnl`	Near-Linear Time Local Polynomial Nonparametric Estimation with Box Kernels. INFORMS J. Comput. Yining Wang, Yi Wu, Simon S. Du
2021	A*	`conf`	Nearly Horizon-Free Offline Reinforcement Learning. NeurIPS Tongzheng Ren, Jialian Li, Bo Dai, Simon S. Du, Sujay Sanghavi
2021	J	`jnl`	Nearly Horizon-Free Offline Reinforcement Learning. CoRR Tongzheng Ren, Jialian Li, Bo Dai, Simon S. Du, Sujay Sanghavi
2021	J	`jnl`	Nearly Optimal Policy Optimization with Stable at Any Time Guarantee. CoRR Tianhao Wu, Yunchang Yang, Han Zhong, Liwei Wang, Simon S. Du, Jiantao Jiao
2021	A*	`conf`	On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP. ICML Tianhao Wu, Yunchang Yang, Simon S. Du, Liwei Wang
2021	J	`jnl`	On the Power of Multitask Representation Learning in Linear MDP. CoRR Rui Lu, Gao Huang, Simon S. Du
2021	J	`jnl`	Provable Adaptation across Multiway Domains via Representation Learning. CoRR Zhili Feng, Shaobo Han, Simon S. Du
2021	J	`jnl`	Provably Efficient Policy Gradient Methods for Two-Player Zero-Sum Markov Games. CoRR Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du
2021	A	`conf`	Q-learning with Logarithmic Regret. AISTATS Kunhe Yang, Lin F. Yang, Simon S. Du
2021	J	`jnl`	Randomized Exploration is Near-Optimal for Tabular MDP. CoRR Zhihan Xiong, Ruoqi Shen, Simon S. Du
2021	A*	`conf`	Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret. NeurIPS Jean Tarbouriech, Runlong Zhou, Simon S. Du, Matteo Pirotta, Michal Valko, Alessandro Lazaric
2021	J	`jnl`	Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret. CoRR Jean Tarbouriech, Runlong Zhou, Simon S. Du, Matteo Pirotta, Michal Valko, Alessandro Lazaric
2021	J	`jnl`	Towards Demystifying Representation Learning with Non-contrastive Self-supervision. CoRR Xiang Wang, Xinlei Chen, Simon S. Du, Yuandong Tian
2021	J	`jnl`	Variance-Aware Confidence Set: Variance-Dependent Bound for Linear Bandits and Horizon-Free Bound for Linear Mixture MDP. CoRR Zihan Zhang, Jiaqi Yang, Xiangyang Ji, Simon S. Du
2021	A	`conf`	When is particle filtering efficient for planning in partially observed linear dynamical systems? UAI Simon S. Du, Wei Hu, Zhiyuan Li, Ruoqi Shen, Zhao Song, Jiajun Wu
2020	A*	`conf`	Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity. NeurIPS Simon S. Du, Jason D. Lee, Gaurav Mahajan, Ruosong Wang
2020	J	`jnl`	Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity. CoRR Simon S. Du, Jason D. Lee, Gaurav Mahajan, Ruosong Wang
2020	A*	`conf`	DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs. IJCAI Yunbo Wang, Bo Liu, Jiajun Wu, Yuke Zhu, Simon S. Du, Li Fei-Fei, Joshua B. Tenenbaum
2020	J	`jnl`	Few-Shot Learning via Learning the Representation, Provably. CoRR Simon S. Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei
2020	A*	`conf`	Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks. ICLR Sanjeev Arora, Simon S. Du, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang, Dingli Yu
2020	J	`jnl`	How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks. CoRR Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
2020	A*	`conf`	Is Long Horizon RL More Difficult Than Short Horizon RL? NeurIPS Ruosong Wang, Simon S. Du, Lin F. Yang, Sham M. Kakade
2020	J	`jnl`	Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning? CoRR Ruosong Wang, Simon S. Du, Lin F. Yang, Sham M. Kakade
2020	J	`jnl`	Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon. CoRR Zihan Zhang, Xiangyang Ji, Simon S. Du
2020	A*	`conf`	Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? ICLR Simon S. Du, Sham M. Kakade, Ruosong Wang, Lin F. Yang
2020	J	`jnl`	Nearly Minimax Optimal Reward-free Reinforcement Learning. CoRR Zihan Zhang, Simon S. Du, Xiangyang Ji
2020	A*	`conf`	On Reward-Free Reinforcement Learning with Linear Function Approximation. NeurIPS Ruosong Wang, Simon S. Du, Lin F. Yang, Ruslan Salakhutdinov
2020	J	`jnl`	On Reward-Free Reinforcement Learning with Linear Function Approximation. CoRR Ruosong Wang, Simon S. Du, Lin F. Yang, Ruslan Salakhutdinov
2020	J	`jnl`	On Stationary-Point Hitting Time and Ergodicity of Stochastic Gradient Langevin Dynamics. J. Mach. Learn. Res. Xi Chen, Simon S. Du, Xin T. Tong
2020	A*	`conf`	Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality. NeurIPS Yi Zhang, Orestis Plevrakis, Simon S. Du, Xingguo Li, Zhao Song, Sanjeev Arora
2020	J	`jnl`	Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality. CoRR Yi Zhang, Orestis Plevrakis, Simon S. Du, Xingguo Li, Zhao Song, Sanjeev Arora
2020	A*	`conf`	Planning with General Objective Functions: Going Beyond Total Rewards. NeurIPS Ruosong Wang, Peilin Zhong, Simon S. Du, Ruslan Salakhutdinov, Lin F. Yang
2020	J	`jnl`	Provable Benefits of Representation Learning in Linear Bandits. CoRR Jiaqi Yang, Wei Hu, Jason D. Lee, Simon S. Du
2020	A*	`conf`	Provable Representation Learning for Imitation Learning via Bi-level Optimization. ICML Sanjeev Arora, Simon S. Du, Sham M. Kakade, Yuping Luo, Nikunj Saunshi
2020	J	`jnl`	Provable Representation Learning for Imitation Learning via Bi-level Optimization. CoRR Sanjeev Arora, Simon S. Du, Sham M. Kakade, Yuping Luo, Nikunj Saunshi
2020	J	`jnl`	Provably Efficient Exploration for RL with Unsupervised Learning. CoRR Fei Feng, Ruosong Wang, Wotao Yin, Simon S. Du, Lin F. Yang
2020	A*	`conf`	Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning. NeurIPS Fei Feng, Ruosong Wang, Wotao Yin, Simon S. Du, Lin F. Yang
2020	J	`jnl`	Q-learning with Logarithmic Regret. CoRR Kunhe Yang, Lin F. Yang, Simon S. Du
2020	A*	`conf`	What Can Neural Networks Reason About? ICLR Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
2020	J	`jnl`	When is Particle Filtering Efficient for POMDP Sequential Planning? CoRR Simon S. Du, Wei Hu, Zhiyuan Li, Ruoqi Shen, Zhao Song, Jiajun Wu
2019	A*	`conf`	Acceleration via Symplectic Discretization of High-Resolution Differential Equations. NeurIPS Bin Shi, Simon S. Du, Weijie J. Su, Michael I. Jordan
2019	J	`jnl`	Acceleration via Symplectic Discretization of High-Resolution Differential Equations. CoRR Bin Shi, Simon S. Du, Weijie J. Su, Michael I. Jordan
2019	J	`jnl`	Continuous Control with Contexts, Provably. CoRR Simon S. Du, Ruosong Wang, Mengdi Wang, Lin F. Yang
2019	J	`jnl`	Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs. CoRR Yunbo Wang, Bo Liu, Jiajun Wu, Yuke Zhu, Simon S. Du, Li Fei-Fei, Joshua B. Tenenbaum
2019	J	`jnl`	Enhanced Convolutional Neural Tangent Kernels. CoRR Zhiyuan Li, Ruosong Wang, Dingli Yu, Simon S. Du, Wei Hu, Ruslan Salakhutdinov, Sanjeev Arora
2019	A*	`conf`	Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks. ICML Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruosong Wang
2019	J	`jnl`	Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks. CoRR Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruosong Wang
2019	J	`jnl`	Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network. CoRR Xiaoxia Wu, Simon S. Du, Rachel A. Ward
2019	A*	`conf`	Gradient Descent Finds Global Minima of Deep Neural Networks. ICML Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai
2019	—	`conf`	Gradient Descent Provably Optimizes Over-parameterized Neural Networks. ICLR (Poster) Simon S. Du, Xiyu Zhai, Barnabás Póczos, Aarti Singh
2019	—	`—`	Gradient Descent for Non-convex Problems in Modern Machine Learning. Simon S. Du
2019	A*	`conf`	Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels. NeurIPS Simon S. Du, Kangcheng Hou, Ruslan Salakhutdinov, Barnabás Póczos, Ruosong Wang, Keyulu Xu
2019	J	`jnl`	Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels. CoRR Simon S. Du, Kangcheng Hou, Barnabás Póczos, Ruslan Salakhutdinov, Ruosong Wang, Keyulu Xu
2019	J	`jnl`	Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks. CoRR Sanjeev Arora, Simon S. Du, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang, Dingli Yu
2019	J	`jnl`	Hitting Time of Stochastic Gradient Langevin Dynamics to Stationary Points: A Direct Analysis. CoRR Xi Chen, Simon S. Du, Xin T. Tong
2019	J	`jnl`	Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? CoRR Simon S. Du, Sham M. Kakade, Ruosong Wang, Lin F. Yang
2019	A	`conf`	Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity. AISTATS Simon S. Du, Wei Hu
2019	A*	`conf`	On Exact Computation with an Infinitely Wide Neural Net. NeurIPS Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang
2019	J	`jnl`	On Exact Computation with an Infinitely Wide Neural Net. CoRR Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang
2019	J	`jnl`	Optimism in Reinforcement Learning with Generalized Linear Function Approximation. CoRR Yining Wang, Ruosong Wang, Simon S. Du, Akshay Krishnamurthy
2019	A*	`conf`	Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle. NeurIPS Simon S. Du, Yuping Luo, Ruosong Wang, Hanrui Zhang
2019	J	`jnl`	Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle. CoRR Simon S. Du, Yuping Luo, Ruosong Wang, Hanrui Zhang
2019	A*	`conf`	Provably efficient RL with Rich Observations via Latent State Decoding. ICML Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford
2019	J	`jnl`	Provably efficient RL with Rich Observations via Latent State Decoding. CoRR Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford
2019	A*	`conf`	Towards Understanding the Importance of Shortcut Connections in Residual Networks. NeurIPS Tianyi Liu, Minshuo Chen, Mo Zhou, Simon S. Du, Enlu Zhou, Tuo Zhao
2019	J	`jnl`	Towards Understanding the Importance of Shortcut Connections in Residual Networks. CoRR Tianyi Liu, Minshuo Chen, Mo Zhou, Simon S. Du, Enlu Zhou, Tuo Zhao
2019	J	`jnl`	What Can Neural Networks Reason About? CoRR Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
2019	A*	`conf`	Width Provably Matters in Optimization for Deep Linear Neural Networks. ICML Simon S. Du, Wei Hu
2019	J	`jnl`	Width Provably Matters in Optimization for Deep Linear Neural Networks. CoRR Simon S. Du, Wei Hu
2018	A*	`conf`	Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced. NeurIPS Simon S. Du, Wei Hu, Jason D. Lee
2018	J	`jnl`	Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced. CoRR Simon S. Du, Wei Hu, Jason D. Lee
2018	A*	`conf`	Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms. ICML Yi Wu, Siddharth Srivastava, Nicholas Hay, Simon S. Du, Stuart Russell
2018	J	`jnl`	Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms. CoRR Yi Wu, Siddharth Srivastava, Nicholas Hay, Simon S. Du, Stuart Russell
2018	A*	`conf`	Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow. ICML Xiao Zhang, Simon S. Du, Quanquan Gu
2018	J	`jnl`	Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow. CoRR Xiao Zhang, Simon S. Du, Quanquan Gu
2018	J	`jnl`	Gradient Descent Finds Global Minima of Deep Neural Networks. CoRR Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai
2018	A*	`conf`	Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima. ICML Simon S. Du, Jason D. Lee, Yuandong Tian, Aarti Singh, Barnabás Póczos
2018	J	`jnl`	Gradient Descent Provably Optimizes Over-parameterized Neural Networks. CoRR Simon S. Du, Xiyu Zhai, Barnabás Póczos, Aarti Singh
2018	A*	`conf`	How Many Samples are Needed to Estimate a Convolutional Neural Network? NeurIPS Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Aarti Singh
2018	J	`jnl`	How Many Samples are Needed to Learn a Convolutional Neural Network? CoRR Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Aarti Singh
2018	J	`jnl`	Improved Learning of One-hidden-layer Convolutional Neural Networks with Overlaps. CoRR Simon S. Du, Surbhi Goel
2018	J	`jnl`	Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity. CoRR Simon S. Du, Wei Hu
2018	J	`jnl`	Near-Linear Time Local Polynomial Nonparametric Estimation. CoRR Yining Wang, Yi Wu, Simon S. Du
2018	A*	`conf`	On the Power of Over-parametrization in Neural Networks with Quadratic Activation. ICML Simon S. Du, Jason D. Lee
2018	J	`jnl`	On the Power of Over-parametrization in Neural Networks with Quadratic Activation. CoRR Simon S. Du, Jason D. Lee
2018	J	`jnl`	Robust Nonparametric Regression under Huber's ε-contamination Model. CoRR Simon S. Du, Yining Wang, Sivaraman Balakrishnan, Pradeep Ravikumar, Aarti Singh
2018	A	`conf`	Stochastic Zeroth-order Optimization in High Dimensions. AISTATS Yining Wang, Simon S. Du, Sivaraman Balakrishnan, Aarti Singh
2018	J	`jnl`	Understanding the Acceleration Phenomenon via High-Resolution Differential Equations. CoRR Bin Shi, Simon S. Du, Michael I. Jordan, Weijie J. Su
2018	—	`conf`	When is a Convolutional Filter Easy to Learn? ICLR (Poster) Simon S. Du, Jason D. Lee, Yuandong Tian
2017	J	`jnl`	Computationally Efficient Robust Estimation of Sparse Functionals. CoRR Simon S. Du, Sivaraman Balakrishnan, Aarti Singh
2017	A*	`conf`	Computationally Efficient Robust Sparse Estimation in High Dimensions. COLT Sivaraman Balakrishnan, Simon S. Du, Jerry Li, Aarti Singh
2017	—	`conf`	Gradient Descent Can Take Exponential Time to Escape Saddle Points. NIPS Simon S. Du, Chi Jin, Jason D. Lee, Michael I. Jordan, Aarti Singh, Barnabás Póczos
2017	J	`jnl`	Gradient Descent Can Take Exponential Time to Escape Saddle Points. CoRR Simon S. Du, Chi Jin, Jason D. Lee, Michael I. Jordan, Barnabás Póczos, Aarti Singh
2017	J	`jnl`	Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima. CoRR Simon S. Du, Jason D. Lee, Yuandong Tian, Barnabás Póczos, Aarti Singh
2017	—	`conf`	High-Throughput Robotic Phenotyping of Energy Sorghum Crops. FSR Srinivasan Vijayarangan, Paloma Sodhi, Prathamesh Kini, James Bourne, Simon S. Du, Hanqi Sun, Barnabás Póczos, Dimitrios Apostolopoulos, David Wettergreen
2017	—	`conf`	Hypothesis Transfer Learning via Transformation Functions. NIPS Simon S. Du, Jayanth Koushik, Aarti Singh, Barnabás Póczos
2017	—	`conf`	On the Power of Truncated SVD for General High-rank Matrix Estimation Problems. NIPS Simon S. Du, Yining Wang, Aarti Singh
2017	J	`jnl`	On the Power of Truncated SVD for General High-rank Matrix Estimation Problems. CoRR Simon S. Du, Yining Wang, Aarti Singh
2017	A*	`conf`	Stochastic Variance Reduction Methods for Policy Evaluation. ICML Simon S. Du, Jianshu Chen, Lihong Li, Lin Xiao, Dengyong Zhou
2017	J	`jnl`	Stochastic Variance Reduction Methods for Policy Evaluation. CoRR Simon S. Du, Jianshu Chen, Lihong Li, Lin Xiao, Dengyong Zhou
2017	J	`jnl`	Stochastic Zeroth-order Optimization in High Dimensions. CoRR Yining Wang, Simon S. Du, Sivaraman Balakrishnan, Aarti Singh
2017	J	`jnl`	When is a Convolutional Filter Easy To Learn? CoRR Simon S. Du, Jason D. Lee, Yuandong Tian
2016	J	`jnl`	An Improved Gap-Dependency Analysis of the Noisy Power Method. CoRR Maria-Florina Balcan, Simon S. Du, Yining Wang, Adams Wei Yu
2016	—	`conf`	Efficient Nonparametric Smoothness Estimation. NIPS Shashank Singh, Simon S. Du, Barnabás Póczos
2016	J	`jnl`	Efficient Nonparametric Smoothness Estimation. CoRR Shashank Singh, Simon S. Du, Barnabás Póczos
2015	A	`conf`	Spectral Gap Error Bounds for Improving CUR Matrix Decomposition and the Nyström Method. AISTATS David G. Anderson, Simon S. Du, Michael W. Mahoney, Christopher Melgaard, Kunming Wu, Ming Gu