Publications

*: indicating equal contribution or alphabetic ordering.

2026

• Improving Human-AI Coordination through Online Adversarial Training and Generative Models
  Paresh Chaudhary, Yancheng Liang, Daphne Chen, Simon S. Du, Natasha Jaques
  International Conference on Learning Representations (ICLR) 2026

• Convergence Dynamics of Over-Parameterized Score Matching for a Single Gaussian
  Yiran Zhang, Weihang Xu, Mo Zhou, Maryam Fazel, Simon S. Du
  International Conference on Learning Representations (ICLR) 2026

• Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail At It
  Shuyue Stella Li*, Avinandan Bose*, Faeze Brahman, Simon Shaolei Du, Pang Wei Koh, Maryam Fazel, Yulia Tsvetkov
  International Conference on Learning Representations (ICLR) 2026

2025

• Understanding the Gain from Data Filtering in Multimodal Contrastive Learning
  Divyansh Pareek, Sewoong Oh, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2025

• Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
  Shulun Chen, Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2025

• Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
  Siting Li, Xiang Gao, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2025

• Reinforcement Learning for Reasoning in Large Language Models with One Training Example
  Yiping Wang, Qing Yang, Zhiyuan Zeng, Liliang Ren, Lucas Liu, Baolin Peng, Hao Cheng, Xuehai He, Kuan Wang, Jianfeng Gao, Weizhu Chen, Shuohang Wang*, Simon S. Du*, Yelong Shen*
  Conference on Neural Information Processing Systems (NeurIPS) 2025

• Deployment Efficient Reward-Free Exploration with Linear Function Approximation
  Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon Shaolei Du, Lin Yang, Ruosong Wang
  Conference on Neural Information Processing Systems (NeurIPS) 2025

• A Minimalist Example of Edge-of-Stability and Progressive Sharpening
  Liming Liu, Zixuan Zhang, Simon Du, Tuo Zhao
  Conference on Neural Information Processing Systems (NeurIPS) 2025

• Transformers are Efficient Compilers, Provably
  Xiyu Zhai, Runlong Zhou, Liao Zhang, Simon Shaolei Du
  Conference on Language Modeling (COLM) 2025

• LoRe: Personalizing LLMs via Low-Rank Reward Modeling
  Avinandan Bose, Zhihan Xiong, Yuejie Chi, Simon S. Du, Lin Xiao, Maryam Fazel
  Conference on Language Modeling (COLM) 2025

• Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback
  Runlong Zhou, Maryam Fazel, Simon S. Du
  Conference on Language Modeling (COLM) 2025

• Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder
  Siting Li, Pang Wei Koh, Simon S. Du
  Annual Meeting of the Association for Computational Linguistics (ACL) 2025

• Anytime Acceleration of Gradient Descent
  Zihan Zhang, Jason D. Lee, Simon S. Du, Yuxin Chen
  Conference of Learning Theory (COLT) 2025

• Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
  Kunal Jha, Wilka Carvalho, Yancheng Liang, Simon S. Du, Max Kleiman-Weiner*, Natasha Jaques*
  International Conference on Machine Learning (ICML) 2025 (Oral)
  

• Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
  Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du, Ruosong Wang
  International Conference on Machine Learning (ICML) 2025
  

• Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation
  Yiping Wang, Xuehai He, Kuan Wang, Luyao Ma, Jianwei Yang, Shuohang Wang, Simon Shaolei Du, Yelong Shen
  Conference on Computer Vision and Pattern Recognition (CVPR) 2025

• The Crucial Role of Samplers in Online Direct Preference Optimization
  Ruizhe Shi*, Runlong Zhou*, Simon S. Du
  International Conference on Learning Representations (ICLR) 2025

• Offline Multi-task Transfer RL with Representational Penalization
  Avinandan Bose, Simon S. Du, Maryam Fazel
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2025

• Optimal Multi-Distribution Learning
  Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
  Journal of the ACM (JACM) 2025 (appeared in part in COLT 2024)

• Settling the Sample Complexity of Online Reinforcement Learning
  Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du
  Journal of the ACM (JACM) 2025 (appeared in part in COLT 2024)

2024

• CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning
  Yiping Wang*, Yifang Chen*, Wendan Yan, Alex Fang, Wenjing Zhou, Kevin Jamieson, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2024 (Spotlight)

• Learning to Cooperate with Humans using Generative Agents
  Yancheng Liang, Daphne Chen, Abhishek Gupta, Simon S. Du*, Natasha Jaques*
  Conference on Neural Information Processing Systems (NeurIPS) 2024

• Understanding the Gains from Repeated Self-Distillation
  Divyansh Pareek, Simon S. Du, Sewoong Oh
  Conference on Neural Information Processing Systems (NeurIPS) 2024

• Decoding-Time Language Model Alignment with Multiple Objectives
  Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hannaneh Hajishirzi, Noah A. Smith, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2024

• Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models
  Weihang Xu, Maryam Fazel, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2024

• Transferable Reinforcement Learning via Generalized Occupancy Models
  Chuning Zhu, Xinqi Wang, Tyler Han, Simon S. Du, Abhishek Gupta
  Conference on Neural Information Processing Systems (NeurIPS) 2024

• Learning Optimal Tax Design in Nonatomic Congestion Games
  Qiwen Cui, Maryam Fazel, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2024

• Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
  Runlong Zhou, Simon S. Du, Beibin Li
  Annual Meeting of the Association for Computational Linguistics (ACL) 2024

• An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
  Gantavya Bhatt*, Yifang Chen*, Arnav M. Das*, Jifan Zhang*, Sang T. Truong, Stephen Mussmann, Yinglun Zhu, Jeffrey Bilmes, Simon S. Du, Kevin Jamieson, Jordan T. Ash, Robert D. Nowak
  Annual Meeting of the Association for Computational Linguistics (ACL) 2024, Findings

• Settling the Sample Complexity of Online Reinforcement Learning
  Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du
  Conference of Learning Theory (COLT) 2024

• Optimal Multi-Distribution Learning
  Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
  Conference of Learning Theory (COLT) 2024

• Refined Sample Complexity for Markov Games with Independent Linear Function Approximation
  Yan Dai, Qiwen Cui, Simon S. Du
  Conference of Learning Theory (COLT) 2024

• Rethinking Transformers in Solving POMDPs
  Chenhao Lu, Ruizhe Shi*, Yuyao Liu*, Kaizhe Hu, Simon S. Du, Huazhe Xu
  International Conference on Machine Learning (ICML) 2024
  

• How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
  Nuoya Xiong, Lijun Ding, Simon S. Du
  International Conference on Learning Representations (ICLR) 2024 (Spotlight)
  

• Horizon-Free Regret for Linear Markov Decision Processes
  Zihan Zhang, Jason D. Lee, Yuxin Chen, Simon S. Du
  International Conference on Learning Representations (ICLR) 2024

• Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
  Zhaoyi Zhou, Chuning Zhu, Runlong Zhou, Qiwen Cui, Abhishek Gupta, Simon S. Du
  International Conference on Learning Representations (ICLR) 2024
  NeurIPS 2023 Foundation Models for Decision Making workshop (Oral)
  [Website] [Video]

• JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention
  Yuandong Tian, Yiping Wang, Zhenyu Zhang, Beidi Chen, Simon S. Du
  International Conference on Learning Representations (ICLR) 2024

• A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
  Haozhe Jiang, Qiwen Cui, Zhihan Xiong, Maryam Fazel, Simon S. Du
  International Conference on Learning Representations (ICLR) 2024

• Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
  Kaifeng Lyu*, Jikai Jin*, Zhiyuan Li, Simon Shaolei Du, Jason D. Lee, Wei Hu
  International Conference on Learning Representations (ICLR) 2024
  

• Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
  Ruizhe Shi*, Yuyao Liu*, Yanjie Ze, Simon S. Du, Huazhe Xu
  International Conference on Learning Representations (ICLR) 2024
  [Website]

• LabelBench: A Comprehensive Framework for Benchmarking Label-Efficient Learning
  Jifan Zhang*, Yifang Chen*, Gregory Canal, Stephen Mussmann, Yinglun Zhu, Simon S. Du, Kevin Jamieson, Robert D Nowak
  Journal of Data-centric Machine Learning Research (DMLR) 2024

2023

• Understanding Curriculum Learning in Policy Optimization for Solving Combinatorial Optimization Problems
  Runlong Zhou, Zelin He, Yuandong Tian, Yi Wu, Simon S. Du
  Transactions on Machine Learning Research (TMLR) 2023

• Active Representation Learning for General Task Space with Applications in Robotics
  Yifang Chen, Yingbing Huang, Simon S. Du, Kevin Jamieson, Guanya Shi
  Conference on Neural Information Processing Systems (NeurIPS) 2023

• Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer
  Yuandong Tian, Yiping Wang, Beidi Chen, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2023
  Selected as Oral presentation at High-dimensional learning dynamics workshop at ICML 2023

• A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
  Yunchang Yang*, Han Zhong*, Tianhao Wu*, Bin Liu, Liwei Wang, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2023

• Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure
  Angela Yuan, Chris Junchi Li, Gauthier Gidel, Michael Jordan, Quanquan Gu, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2023

• Integrating Traffic Science with Representation Learning for City-wide Network Congestion Prediction
  Wenqing Zheng*, Hao Yang*, Jiarui Cai, Peihao Wang, Xuan Jiang, Simon S. Du, Yinhai Wang, Zhangyang Wang
  Information Fusion 2023

• Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron
  Weihang Xu, Simon S. Du
  Conference of Learning Theory (COLT) 2023
  Selected as Oral presentation at High-dimensional learning dynamics workshop at ICML 2023

• Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation
  Qiwen Cui, Kaiqing Zhang, Simon S. Du
  Conference of Learning Theory (COLT) 2023

• On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness
  Haotian Ye*, Xiaoyu Chen*, Liwei Wang, Simon S. Du
  International Conference on Machine Learning (ICML) 2023 (Oral)
  

• Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
  Runlong Zhou, Zihan Zhang, Simon S. Du
  International Conference on Machine Learning (ICML) 2023
  

• Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
  Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon S. Du, Jason D. Lee
  International Conference on Machine Learning (ICML) 2023
  

• Horizon-Free Reinforcement Learning for Latent Markov Decision Processes
  Runlong Zhou, Ruosong Wang, Simon S. Du
  International Conference on Machine Learning (ICML) 2023
  

• Improved Active Multi-Task Representation Learning via Lasso
  Yiping Wang, Yifang Chen, Kevin Jamieson, Simon S. Du
  International Conference on Machine Learning (ICML) 2023
  

• Offline congestion games: How feedback type affects data coverage requirement
  Haozhe Jiang*, Qiwen Cui*, Zhihan Xiong, Maryam Fazel, Simon S. Du
  International Conference on Learning Representations (ICLR) 2023
  

• Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
  Shicong Cen, Yuejie Chi, Simon S. Du, Lin Xiao
  International Conference on Learning Representations (ICLR) 2023
  

• Variance-Aware Sparse Linear Bandits
  Yan Dai, Ruosong Wang, Simon S. Du
  International Conference on Learning Representations (ICLR) 2023
  

• Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies
  Rui Yuan, Simon S. Du, Robert M. Gower, Alessandro Lazaric, Lin Xiao
  International Conference on Learning Representations (ICLR) 2023
  

• Blessing of Class Diversity in Pre-training
  Yulai Zhao, Jianshu Chen, Simon S. Du
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2023 (Notable Paper)

• Beyond Information Gain: An Empirical Benchmark for Low-Switching-Cost Reinforcement Learning
  Shusheng Xu, Yancheng Liang, Yunfei Li, Simon S. Du, Yi Wu
  Transactions on Machine Learning Research (TMLR) 2023

2022

• Learning in Congestion Games with Bandit Feedback
  Qiwen Cui*, Zhihan Xiong*, Maryam Fazel, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2022

• On Gap-dependent Bounds for Offline Reinforcement Learning
  Xinqi Wang, Qiwen Cui, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2022

• Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus
  Qiwen Cui, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2022

• Provable General Function Class Representation Learning in Multitask Bandits and MDPs
  Rui Lu, Andrew Zhao, Simon S. Du, Gao Huang
  Conference on Neural Information Processing Systems (NeurIPS) 2022 (Spotlight)

• When is Offline Two-Player Zero-Sum Markov Game Solvable?
  Qiwen Cui, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2022

• Near-Optimal Randomized Exploration for Tabular MDP
  Zhihan Xiong*, Ruoqi Shen*, Qiwen Cui*, Maryam, Fazel, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2022

• Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies
  Zihan Zhang, Xiangyang Ji, Simon S. Du
  Conference of Learning Theory (COLT) 2022

• Active Multi-Task Representation Learning
  Yifang Chen, Simon S. Du, Kevin Jamieson
  International Conference on Machine Learning (ICML) 2022
  

• Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path
  Haoyuan Cai, Tengyu Ma, Simon S. Du
  International Conference on Machine Learning (ICML) 2022
  

• Denoised MDPs: Learning World Models Better Than the World Itself
  Tongzhou Wang, Simon S. Du, Antonio Torralba, Phillip Isola, Amy Zhang, Yuandong Tian
  International Conference on Machine Learning (ICML) 2022
  [Project Page] [Code]

• Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes
  Andrew Wagenmaker, Yifang Chen, Max Simchowitz, Simon S. Du, Kevin Jamieson
  International Conference on Machine Learning (ICML) 2022
  

• Nearly Optimal Policy Optimization with Stable at Any Time Guarantee
  Tianhao Wu*, Yunchang Yang*, Han Zhong*, Liwei Wang, Simon S. Du, Jiantao Jiao
  International Conference on Machine Learning (ICML) 2022
  

• First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
  Andrew Wagenmaker, Yifang Chen, Max Simchowitz, Simon S. Du, Kevin Jamieson
  International Conference on Machine Learning (ICML) 2022 (Long talk)
  

• Provable Adaptation across Multiway Domains via Representation Learning
  Zhili Feng, Shaobo Han, Simon S. Du
  International Conference on Learning Representations (ICLR) 2022
  

• A Unified Framework for Conservative Exploration
  Yunchang Yang*, Tianhao Wu*, Han Zhong*, Evrard Garcelon, Matteo Pirotta, Alessandro Lazaric, Liwei Wang, Simon S. Du
  International Conference on Learning Representations (ICLR) 2022
  

• Provably Efficient Policy Gradient Methods for Two-Player Zero-Sum Markov Games
  Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2022

• Gap-Dependent Bounds for Two-Player Markov Games
  Zehao Dou, Zhuoran Yang, Zhaoran Wang, Simon S. Du
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2022

• AdaLoss: A Computationally-Efficient and Provably Convergent Adaptive Gradient Method
  Xiaoxia Wu, Yuege Xie, Simon S. Du, Rachel Ward
  AAAI Conference on Artificial Intelligence (AAAI) 2022

• Understanding the Acceleration Phenomenon via High-Resolution Differential Equations
  Bin Shi, Simon S. Du, Michael I. Jordan, Weijie J. Su
  Mathematical Programming Series A, 2022

2021

• Corruption Robust Active Learning
  Yifang Chen, Simon S. Du, Kevin Jamieson
  Conference on Neural Information Processing Systems (NeurIPS) 2021

• Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization
  Tian Ye, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2021

• Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP
  Zihan Zhang*, Jiaqi Yang*, Xiangyang Ji, Simon S. Du
  Conference on Neural Information Processing Systems (NeurIPS) 2021

• Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret
  Jean Tarbouriech*, Runlong Zhou*, Simon S. Du, Matteo Pirotta, Michal Valko, Alessandro Lazaric
  Conference on Neural Information Processing Systems (NeurIPS) 2021 (Spotlight)
  [Talk]

• Nearly Horizon-Free Offline Reinforcement Learning
  Tongzheng Ren, Jialian Li, Bo Dai, Simon S. Du, Sujay Sanghavi
  Conference on Neural Information Processing Systems (NeurIPS) 2021

• Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon
  Zihan Zhang, Xiangyang Ji, Simon S. Du
  Conference of Learning Theory (COLT) 2021
  [Talk]

• Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap
  Haike Xu, Tengyu Ma, Simon S. Du
  Conference of Learning Theory (COLT) 2021

• When is Particle Filtering Efficient for Planning in Partially Observed Linear Dynamical Systems?
  Simon S. Du*, Wei Hu*, Zhiyuan Li*, Ruoqi Shen*, Zhao Song*, Jiajun Wu*
  Conference on Uncertainty in Artificial Intelligence (UAI) 2021

• Bilinear Classes: A Structural Framework for Provable Generalization in RL
  Simon S. Du*, Sham M. Kakade*, Jason D. Lee*, Shachar Lovett*, Gaurav Mahajan*, Wen Sun*, Ruosong Wang*
  International Conference on Machine Learning (ICML) 2021 (Long talk)
  [Talk]

• Nearly Minimax Optimal Reward-free Reinforcement Learning
  Zihan Zhang, Simon S. Du, Xiangyang Ji
  International Conference on Machine Learning (ICML) 2021 (Long talk)
  [Talk]

• Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
  Yifang Chen, Simon S. Du, Kevin Jamieson
  International Conference on Machine Learning (ICML) 2021

• On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP
  Tianhao Wu*, Yunchang Yang*, Simon S. Du, Liwei Wang
  International Conference on Machine Learning (ICML) 2021

• Q-learning with Logarithmic Regret
  Kunhe Yang, Lin F. Yang, Simon S. Du
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2021
  

• Impact of Representation Learning in Linear Bandits
  Jiaqi Yang, Wei Hu, Jason D. Lee, Simon S. Du
  International Conference on Learning Representations (ICLR) 2021
  

• Few-Shot Learning via Learning the Representation, Provably
  Simon S. Du*, Wei Hu*, Sham M. Kakade*, Jason D. Lee*, Qi Lei*
  International Conference on Learning Representations (ICLR) 2021
  

• How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
  Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
  International Conference on Learning Representations (ICLR) 2021 (Oral)
  

• Optimism in Reinforcement Learning with Generalized Linear Function Approximation
  Yining Wang, Ruosong Wang, Simon S. Du, Akshay Krishnamurthy
  International Conference on Learning Representations (ICLR) 2021
  

• Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization
  Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon S. Du, Yu Wang, Yi Wu
  International Conference on Learning Representations (ICLR) 2021

2020

• Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?
  Ruosong Wang*, Simon S. Du*, Lin F. Yang*, Sham M. Kakade
  Conference on Neural Information Processing Systems (NeurIPS) 2020

• Planning with General Objective Functions: Going Beyond Total Rewards
  Ruosong Wang*, Peilin Zhong*, Simon S. Du, Ruslan Salakhutdinov, Lin F. Yang
  Conference on Neural Information Processing Systems (NeurIPS) 2020

• On Reward-Free Reinforcement Learning with Linear Function Approximation
  Ruosong Wang, Simon S. Du, Lin F. Yang, Ruslan Salakhutdinov
  Conference on Neural Information Processing Systems (NeurIPS) 2020

• Provably Efficient Exploration for RL with Unsupervised Learning
  Fei Feng, Ruosong Wang, Wotao Yin, Simon S. Du, Lin F. Yang
  Conference on Neural Information Processing Systems (NeurIPS) 2020 (Spotlight)
  [Talk]

• Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity
  Simon S. Du*, Jason D. Lee*, Gaurav Mahajan*, Ruosong Wang*
  Conference on Neural Information Processing Systems (NeurIPS) 2020

• Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
  Yi Zhang*, Orestis Plevrakis*, Simon S. Du, Xingguo Li, Zhao Song, Sanjeev Arora
  Conference on Neural Information Processing Systems (NeurIPS) 2020

• Near-Linear Time Local Polynomial Nonparametric Estimation
  Yining Wang, Yi Wu, Simon S. Du
  Informs Journal on Computing 2020

• Provable Representation Learning for Imitation Learning via Bi-level Optimization
  Sanjeev Arora*, Simon S. Du*, Sham Kakade*, Yuping Luo*, Nikunj Saunshi*
  International Conference on Machine Learning (ICML) 2020

• Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs
  Yunbo Wang*, Bo Liu*, Jiajun Wu, Yuke Zhu, Simon S. Du, Li Fei-Fei, Joshua B. Tenenbaum
  International Joint Conference on Artificial Intelligence (IJCAI) 2020

• On Stationary-Point Hitting Time and Ergodicity of Stochastic Gradient Langevin Dynamics
  Xi Chen*, Simon S. Du*, Xin T. Tong*
  Jounrnal of Machine Learning Research (JMLR) 2020

• Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?
  Simon S. Du*, Sham M. Kakade*, Ruosong Wang*, Lin F. Yang*
  International Conference on Learning Representations (ICLR) 2020 (Spotlight)
  Selected as Late-Breaking Paper in NeurIPS 2019 Deep Reinforcement Learning Workshop
  

• Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
  Sanjeev Arora*, Simon S. Du*, Zhiyuan Li*, Ruslan Salakhutdinov*, Ruosong Wang*, Dingli Yu*
  International Conference on Learning Representations (ICLR) 2020 (Spotlight)
  [Code]

• What Can Neural Networks Reason About?
  Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
  International Conference on Learning Representations (ICLR) 2020 (Spotlight)
  

2019

• Gradient Descent for Non-convex Problems in Modern Machine Learning
  Simon S. Du
  PhD thesis, Machine Learning Department, Carnegie Mellon University
  CMU SCS Dissertation Award Honorable Mention
  Nominations for ACM Dissertation Award and AAAI SIGAI Dissertation Award

• Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle
  Simon S. Du*, Yuping Luo*, Ruosong Wang*, Hanrui Zhang*
  Conference on Neural Information Processing Systems (NeurIPS) 2019

• Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
  Simon S. Du*, Kangcheng Hou*, Barnabás Póczos*, Ruslan Salakhutdinov*, Ruosong Wang*, Keyulu Xu*
  Conference on Neural Information Processing Systems (NeurIPS) 2019
  [Code]

• On Exact Computation with an Infinitely Wide Neural Net
  Sanjeev Arora*, Simon S. Du*, Wei Hu*, Zhiyuan Li*, Ruslan Salakhutdinov*, Ruosong Wang*
  Conference on Neural Information Processing Systems (NeurIPS) 2019 (Spotlight)
  [Code] [Blog]

• Acceleration via Symplectic Discretization of High-Resolution Differential Equations
  Bin Shi, Simon S. Du, Weijie Su, Michael I. Jordan
  Conference on Neural Information Processing Systems (NeurIPS) 2019

• Towards Understanding the Importance of Shortcut Connections in Residual Networks
  Tianyi Liu*, Minshuo Chen*, Mo Zhou, Simon S. Du, Enlu Zhou and Tuo Zhao
  Conference on Neural Information Processing Systems (NeurIPS) 2019

• Provably efficient RL with Rich Observations via Latent State Decoding
  Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford
  International Conference on Machine Learning (ICML) 2019
  [Code] [Blog]

• Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks
  Sanjeev Arora*, Simon S. Du*, Wei Hu*, Zhiyuan Li*, Ruosong Wang*
  International Conference on Machine Learning (ICML) 2019

• Width Provably Matters in Optimization for Deep Linear Neural Networks
  Simon S. Du*, Wei Hu*
  International Conference on Machine Learning (ICML) 2019

• Gradient Descent Finds Global Minima of Deep Neural Networks
  Simon S. Du*, Jason D. Lee*, Haochuan Li*, Liwei Wang*, Xiyu Zhai*
  International Conference on Machine Learning (ICML) 2019

• Gradient Descent Provably Optimizes Over-parameterized Neural Networks
  Simon S. Du*, Xiyu Zhai*, Barnabás Póczos, Aarti Singh
  International Conference on Learning Representations (ICLR) 2019

• Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity
  Simon S. Du*, Wei Hu*
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2019

2018

• Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced
  Simon S. Du*, Wei Hu*, Jason D. Lee*
  Conference on Neural Information Processing Systems (NeurIPS) 2018
  ICML 2018 Workshop on Nonconvex Optimization Best Paper Award

• How Many Samples are Needed to Learn a Convolutional Neural Network?
  Simon S. Du*, Yining Wang*, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Aarti Singh
  Conference on Neural Information Processing Systems (NeurIPS) 2018
  [Forbes Article] NVIDIA Pioneer Award

• Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima
  Simon S. Du, Jason D. Lee, Yuandong Tian, Barnabás Póczos, Aarti Singh
  International Conference on Machine Learning (ICML) 2018 (Long Talk)

• On the Power of Over-parametrization in Neural Networks with Quadratic Activation
  Simon S. Du, Jason D. Lee
  International Conference on Machine Learning (ICML) 2018.

• Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow
  Xiao Zhang*, Simon S. Du*, Quanquan Gu
  International Conference on Machine Learning (ICML) 2018

• Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms
  Yi Wu, Siddharth Srivastava, Nick Hay, Simon S. Du, Stuart Russell
  International Conference on Machine Learning (ICML) 2018

• When is a Convolutional Filter Easy to Learn?
  Simon S. Du, Jason D. Lee, Yuandong Tian
  International Conference on Learning Representations (ICLR) 2018

• Stochastic Zeroth-order Optimization in High Dimensions
  Yining Wang, Simon S. Du, Sivaraman Balakrishnan, Aarti Singh
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2018 (Oral)

2017

• Gradient Descent Can Take Exponential Time to Escape Saddle Points
  Simon S. Du, Chi Jin, Jason D. Lee, Michael I. Jordan, Barnabás Póczos, Aarti Singh
  Conference on Neural Information Processing Systems (NIPS) 2017 (Spotlight)

• On the Power of Truncated SVD for General High-rank Matrix Estimation Problems
  Simon S. Du, Yining Wang, Aarti Singh
  Conference on Neural Information Processing Systems (NIPS) 2017

• Hypothesis Transfer Learning via Transformation Functions
  Simon S. Du, Jayanth Koushik, Aarti Singh, Barnabás Póczos
  Conference on Neural Information Processing Systems (NIPS) 2017

• High-throughput Robotic Phenotyping of Energy Sorghum Crops
  Srinivasan Vijayarangan, Paloma Sodhi, Prathamesh Kini, James Bourne, Simon S. Du, Hanqi Sun, Barnabás Póczos, Dimitrios Apostolopoulos, and David Wettergreen
  Conference on Field and Service Robotics (FSR) 2017

• Stochastic Variance Reduction Methods for Policy Evaluation
  Simon S. Du, Jianshu Chen, Lihong Li, Lin Xiao, Dengyong Zhou
  International Conference on Machine Learning (ICML) 2017
  

• Computationally Efficient Robust Estimation of Sparse Functionals
  Simon S. Du, Sivaraman Balakrishnan, Aarti Singh
  Conference of Learning Theory (COLT) 2017
  Merged with this paper

2016

• Efficient Nonparametric Smoothness Estimation
  Shashank Singh, Simon S. Du Barnabás Póczos
  Conference on Neural Information Processing Systems (NIPS) 2016

• An Improved Gap-Dependency Analysis of the Noisy Power Method
  Maria-Florina Balcan*, Simon S. Du*, Yining Wang*, Adams Wei Yu*
  Conference of Learning Theory (COLT) 2016

2015

• Spectral Gap Error Bounds for Improving CUR Matrix Decomposition and the Nystrom Method
  David G. Anderson*, Simon S. Du*, Michael W. Mahoney*, Christopher Melgaard*, Kunming Wu*, Ming Gu*
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2015

Preprints and Technical Reports

• Cold-Start Personalization via Training-Free Priors from Structured World Models
  Avinandan Bose, Shuyue Stella Li, Faeze Brahman, Pang Wei Koh, Simon Shaolei Du, Yulia Tsvetkov, Maryam Fazel, Lin Xiao, Asli Celikyilmaz

• ThetaEvolve: Test-time Learning on Open Problems
  Yiping Wang, Shao-Rong Su, Zhiyuan Zeng, Eva Xu, Liliang Ren, Xinyu Yang, Zeyi Huang, Xuehai He, Luyao Ma, Baolin Peng, Hao Cheng, Pengcheng He, Weizhu Chen, Shuohang Wang, Simon Shaolei Du*, Yelong Shen*

• RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
  Zhiyuan Zeng*, Hamish Ivison*, Yiping Wang*, Lifan Yuan*, Shuyue Stella Li, Zhuorui Ye, Siting Li, Jacqueline He, Runlong Zhou, Tong Chen, Chenyang Zhao, Yulia Tsvetkov, Simon Shaolei Du, Natasha Jaques, Hao Peng, Pang Wei Koh, Hannaneh Hajishirzi

• Spurious Rewards: Rethinking Training Signals in RLVR
  Rulin Shao*, Shuyue Stella Li*, Rui Xin*, Scott Geng*, Yiping Wang, Sewoong Oh, Simon S. Du, Nathan Lambert, Sewon Min, Ranjay Krishna, Yulia Tsvetkov, Hannaneh Hajishirzi, Pang Wei Koh, Luke Zettlemoyer

• Policy-Based Trajectory Clustering in Offline Reinforcement Learning
  Hao Hu*, Xinqi Wang*, Simon S. Du

• Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
  Mickel Liu*, Liwei Jiang*, Yancheng Liang, Simon S. Du, Yejin Choi, Tim Althoff, Natasha Jaques

• Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures
  Mo Zhou*, Weihang Xu*, Maryam Fazel, Simon S. Du

• Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
  Ruizhe Shi*, Minhak Song*, Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du

• SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters
  Yiping Wang, Hanxian Huang, Yifang Chen, Jishen Zhao, Simon Shaolei Du, Yuandong Tian

• Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration
  Avinandan Bose, Zhihan Xiong, Aadirupa Saha, Simon Shaolei Du, Maryam Fazel

• Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation
  Yifang Chen, David Zhu, Simon S. Du, Kevin Jamieson, Yang Liu

• Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques
  Natalia Zhang*, Xinqi Wang*, Qiwen Cui*, Runlong Zhou, Sham M. Kakade, Simon S. Du

• Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning
  Yifang Chen, Shuohang Wang, Ziyi Yang, Hiteshi Sharma, Nikos Karampatziakis, Donghan Yu, Kevin Jamieson, Simon Shaolei Du, Yelong Shen

• TransFollower: Long-Sequence Car-Following Trajectory Prediction through Transformer
  Meixin Zhu, Simon S. Du, Xuesong Wang, Hao, Yang, Ziyuan Pu, Yinhai Wang

• A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost
  Minbo Gao*, Tianle Xie*, Simon S. Du, Lin F. Yang

• Towards Demystifying Representation Learning with Non-contrastive Self-supervision
  Xiang Wang, Xinlei Chen, Simon S. Du, Yuandong Tian

• Enhanced Convolutional Neural Tangent Kernels
  Zhiyuan Li*, Ruosong Wang*, Dingli Yu*, Simon S. Du, Wei Hu, Ruslan Salakhutdinov, Sanjeev Arora

• Continuous Control with Contexts, Provably
  Simon S. Du*, Ruosong Wang*, Mengdi Wang*, Lin F. Yang*

• Improved Learning of One-hidden-layer Convolutional Neural Networks with Overlaps
  Simon S. Du*, Surbhi Goel*.

• Robust Nonparametric Regression under Huber's epsilon-contamination Model
  Simon S. Du, Yining Wang, Sivaraman Balakrishnan, Pradeep Ravikumar, Aarti Singh