Simon S. Du

is this you? claim profile

∙

0 followers

∙

Institute for Advanced Study

∙

Carnegie Mellon University

∙

University of Washington

Research Intern at facebook 2017, Research Intern at Microsoft 2016, Consulting Intern at Accenture 2015, Research Assistant at UC Berkeley from 2013-2014, Software Engineering Intern at Google 2014, Research Assistant at Bay Area Intellectual Property Group 2013, Consulting Intern at CCID Consulting Co. 2012, PhD in Machine Learning Department at Carnegie Mellon University 2015-2020

Featured Co-authors

Michael I. Jordan
252 publications
Xi Chen
217 publications
Yi Zhang
182 publications
Ruslan Salakhutdinov
173 publications
Joshua B. Tenenbaum
138 publications
Bo Liu
131 publications
Antonio Torralba
124 publications
Liwei Wang
124 publications
Li Fei-Fei
120 publications
Quanquan Gu
104 publications
Barnabas Poczos
99 publications

∙ 06/30/2022

Denoised MDPs: Learning World Models Better Than the World Itself

The ability to separate signal from noise, and reason with clean abstrac...

Tongzhou Wang, et al. ∙

∙ 06/17/2022

Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization

We consider the smooth convex-concave bilinearly-coupled saddle-point pr...

Simon S. Du, et al. ∙

∙ 06/04/2022

Learning in Congestion Games with Bandit Feedback

Learning Nash equilibria is a central problem in multi-agent systems. In...

Qiwen Cui, et al. ∙

∙ 06/01/2022

On Gap-dependent Bounds for Offline Reinforcement Learning

This paper presents a systematic study on gap-dependent sample complexit...

Xinqi Wang, et al. ∙

∙ 06/01/2022

Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus

This paper considers offline multi-agent reinforcement learning. We prop...

Qiwen Cui, et al. ∙

∙ 05/31/2022

Provable General Function Class Representation Learning in Multitask Bandits and MDPs

While multitask representation learning has become a popular approach in...

Rui Lu, et al. ∙

∙ 05/26/2022

Variance-Aware Sparse Linear Bandits

It is well-known that the worst-case minimax regret for sparse linear ba...

Yan Dai, et al. ∙

∙ 03/29/2022

Nearly Minimax Algorithms for Linear Bandits with Shared Representation

We give novel algorithms for multi-task and lifelong linear bandits with...

Jiaqi Yang, et al. ∙

∙ 03/24/2022

Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies

This paper gives the first polynomial-time algorithm for tabular Markov ...

Zihan Zhang, et al. ∙

∙ 02/11/2022

Understanding Curriculum Learning in Policy Optimization for Solving Combinatorial Optimization Problems

Over the recent years, reinforcement learning (RL) has shown impressive ...

Runlong Zhou, et al. ∙

∙ 02/04/2022

TransFollower: Long-Sequence Car-Following Trajectory Prediction through Transformer

Car-following refers to a control process in which the following vehicle...

Meixin Zhu, et al. ∙

∙ 02/02/2022

Active Multi-Task Representation Learning

To leverage the power of big data from source tasks and overcome the sca...

Yifang Chen, et al. ∙

∙ 01/26/2022

Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes

Reward-free reinforcement learning (RL) considers the setting where the ...

Andrew Wagenmaker, et al. ∙

∙ 01/10/2022

When is Offline Two-Player Zero-Sum Markov Game Solvable?

We study what dataset assumption permits solving offline two-player zero...

Qiwen Cui, et al. ∙

∙ 12/21/2021

Nearly Optimal Policy Optimization with Stable at Any Time Guarantee

Policy optimization methods are one of the most widely used classes of R...

Tianhao Wu, et al. ∙

∙ 12/07/2021

First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach

Obtaining first-order regret bounds – regret bounds scaling not as the w...

Andrew Wagenmaker, et al. ∙

∙ 10/11/2021

Towards Demystifying Representation Learning with Non-contrastive Self-supervision

Non-contrastive methods of self-supervised learning (such as BYOL and Si...

Xiang Wang, et al. ∙

∙ 07/01/2021

Gap-Dependent Bounds for Two-Player Markov Games

As one of the most popular methods in the field of reinforcement learnin...

Zehao Dou, et al. ∙

∙ 06/27/2021

Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization

We study the asymmetric low-rank factorization problem: min_𝐔∈ℝ^m ×...

Tian Ye, et al. ∙

∙ 06/22/2021

A Unified Framework for Conservative Exploration

We study bandits and reinforcement learning (RL) subject to a conservati...

Yunchang Yang, et al. ∙

∙ 06/21/2021

Corruption Robust Active Learning

We conduct theoretical studies on streaming-based active learning for bi...

Yifang Chen, et al. ∙

∙ 06/15/2021

On the Power of Multitask Representation Learning in Linear MDP

While multitask representation learning has become a popular approach in...

Rui Lu, et al. ∙

∙ 06/12/2021

Provable Adaptation across Multiway Domains via Representation Learning

This paper studies zero-shot domain adaptation where each domain is inde...

Zhili Feng, et al. ∙

∙ 04/22/2021

Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret

We study the problem of learning in the stochastic shortest path (SSP) s...

Jean Tarbouriech, et al. ∙

∙ 03/25/2021

Nearly Horizon-Free Offline Reinforcement Learning

We revisit offline reinforcement learning on episodic time-homogeneous t...

Tongzheng Ren, et al. ∙

∙ 03/19/2021

Bilinear Classes: A Structural Framework for Provable Generalization in RL

This work introduces Bilinear Classes, a new structural framework, which...

Simon S. Du, et al. ∙

∙ 02/19/2021

Randomized Exploration is Near-Optimal for Tabular MDP

We study exploration using randomized value functions in Thompson Sampli...

Zhihan Xiong, et al. ∙

∙ 02/17/2021

Provably Efficient Policy Gradient Methods for Two-Player Zero-Sum Markov Games

Policy gradient methods are widely used in solving two-player zero-sum g...

Yulai Zhao, et al. ∙

∙ 02/13/2021

Improved Corruption Robust Algorithms for Episodic Reinforcement Learning

We study episodic reinforcement learning under unknown adversarial corru...

Yifang Chen, et al. ∙

∙ 02/09/2021

Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap

This paper presents a new model-free algorithm for episodic finite-horiz...

Haike Xu, et al. ∙

∙ 01/29/2021

Variance-Aware Confidence Set: Variance-Dependent Bound for Linear Bandits and Horizon-Free Bound for Linear Mixture MDP

We show how to construct variance-aware confidence sets for linear bandi...

Zihan Zhang, et al. ∙

∙ 01/02/2021

A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost

Many real-world applications, such as those in medical domains, recommen...

Minbo Gao, et al. ∙

∙ 10/12/2020

Nearly Minimax Optimal Reward-free Reinforcement Learning

We study the reward-free reinforcement learning framework, which is part...

Zihan Zhang, et al. ∙

∙ 09/28/2020

Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon

Episodic reinforcement learning and contextual bandits are two widely st...

Zihan Zhang, et al. ∙

∙ 09/24/2020

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks

We study how neural networks trained by gradient descent extrapolate, i....

Keyulu Xu, et al. ∙

∙ 06/19/2020

On Reward-Free Reinforcement Learning with Linear Function Approximation

Reward-free reinforcement learning (RL) is a framework which is suitable...

Ruosong Wang, et al. ∙

∙ 06/16/2020

Q-learning with Logarithmic Regret

This paper presents the first non-asymptotic result showing that a model...

Kunhe Yang, et al. ∙

∙ 06/10/2020

When is Particle Filtering Efficient for POMDP Sequential Planning?

Particle filtering is a popular method for inferring latent states in st...

Simon S. Du, et al. ∙

∙ 05/01/2020

Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?

Learning to plan for long horizons is a central challenge in episodic re...

Ruosong Wang, et al. ∙

∙ 03/15/2020

Provably Efficient Exploration for RL with Unsupervised Learning

We study how to use unsupervised learning for efficient exploration in r...

Fei Feng, et al. ∙

∙ 02/24/2020

Provable Representation Learning for Imitation Learning via Bi-level Optimization

A common strategy in modern learning systems is to learn a representatio...

Sanjeev Arora, et al. ∙

∙ 02/21/2020

Few-Shot Learning via Learning the Representation, Provably

This paper studies few-shot learning via representation learning, where ...

Simon S. Du, et al. ∙

∙ 02/17/2020

Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity

The current paper studies the problem of agnostic Q-learning with functi...

Simon S. Du, et al. ∙

∙ 02/16/2020

Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality

Adversarial training is a popular method to give neural nets robustness ...

Yi Zhang, et al. ∙

∙ 12/09/2019

Optimism in Reinforcement Learning with Generalized Linear Function Approximation

We design a new provably efficient algorithm for episodic reinforcement ...

Yining Wang, et al. ∙

∙ 11/03/2019

Enhanced Convolutional Neural Tangent Kernels

Recent research shows that for training with ℓ_2 loss, convolutional neu...

Zhiyuan Li, et al. ∙

∙ 10/30/2019

Continuous Control with Contexts, Provably

A fundamental challenge in artificial intelligence is to build an agent ...

Simon S. Du, et al. ∙

∙ 10/07/2019

Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?

Modern deep learning methods provide an effective means to learn good re...

Simon S. Du, et al. ∙

∙ 10/03/2019

Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

Recent research shows that the following two models are equivalent: (a) ...

Sanjeev Arora, et al. ∙

∙ 09/28/2019

Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs

We present the DualSMC network that solves continuous POMDPs by learning...

Yunbo Wang, et al. ∙