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

May 01, 2020
Ruosong Wang, Simon S. Du, Lin F. Yang, Sham M. Kakade


  Access Model/Code and Paper
Provably Efficient Exploration for RL with Unsupervised Learning

Mar 15, 2020
Fei Feng, Ruosong Wang, Wotao Yin, Simon S. Du, Lin F. Yang


  Access Model/Code and Paper
Provable Representation Learning for Imitation Learning via Bi-level Optimization

Feb 24, 2020
Sanjeev Arora, Simon S. Du, Sham Kakade, Yuping Luo, Nikunj Saunshi

* 26 pages 

  Access Model/Code and Paper
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality

Feb 24, 2020
Yi Zhang, Orestis Plevrakis, Simon S. Du, Xingguo Li, Zhao Song, Sanjeev Arora


  Access Model/Code and Paper
Few-Shot Learning via Learning the Representation, Provably

Feb 21, 2020
Simon S. Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei


  Access Model/Code and Paper
Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity

Feb 17, 2020
Simon S. Du, Jason D. Lee, Gaurav Mahajan, Ruosong Wang


  Access Model/Code and Paper
Optimism in Reinforcement Learning with Generalized Linear Function Approximation

Dec 09, 2019
Yining Wang, Ruosong Wang, Simon S. Du, Akshay Krishnamurthy


  Access Model/Code and Paper
Enhanced Convolutional Neural Tangent Kernels

Nov 03, 2019
Zhiyuan Li, Ruosong Wang, Dingli Yu, Simon S. Du, Wei Hu, Ruslan Salakhutdinov, Sanjeev Arora


  Access Model/Code and Paper
Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?

Nov 03, 2019
Simon S. Du, Sham M. Kakade, Ruosong Wang, Lin F. Yang


  Access Model/Code and Paper
Continuous Control with Contexts, Provably

Oct 30, 2019
Simon S. Du, Ruosong Wang, Mengdi Wang, Lin F. Yang


  Access Model/Code and Paper
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

Oct 27, 2019
Sanjeev Arora, Simon S. Du, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang, Dingli Yu

* Code for UCI experiments: https://github.com/LeoYu/neural-tangent-kernel-UCI 

  Access Model/Code and Paper
Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs

Sep 28, 2019
Yunbo Wang, Bo Liu, Jiajun Wu, Yuke Zhu, Simon S. Du, Li Fei-Fei, Joshua B. Tenenbaum


  Access Model/Code and Paper
Towards Understanding the Importance of Shortcut Connections in Residual Networks

Sep 11, 2019
Tianyi Liu, Minshuo Chen, Mo Zhou, Simon S. Du, Enlu Zhou, Tuo Zhao

* Thirty-third Conference on Neural Information Processing Systems, 2019 

  Access Model/Code and Paper
Provably Efficient $Q$-learning with Function Approximation via Distribution Shift Error Checking Oracle

Jun 14, 2019
Simon S. Du, Yuping Luo, Ruosong Wang, Hanrui Zhang


  Access Model/Code and Paper
What Can Neural Networks Reason About?

May 31, 2019
Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka


  Access Model/Code and Paper
Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

May 30, 2019
Simon S. Du, Kangcheng Hou, Barnabás Póczos, Ruslan Salakhutdinov, Ruosong Wang, Keyulu Xu


  Access Model/Code and Paper
Hitting Time of Stochastic Gradient Langevin Dynamics to Stationary Points: A Direct Analysis

May 29, 2019
Xi Chen, Simon S. Du, Xin T. Tong

* 31 pages 

  Access Model/Code and Paper
On Exact Computation with an Infinitely Wide Neural Net

Apr 26, 2019
Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang

* abstract shortened to meet the constraint 

  Access Model/Code and Paper
Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network

Feb 19, 2019
Xiaoxia Wu, Simon S. Du, Rachel Ward


  Access Model/Code and Paper
Acceleration via Symplectic Discretization of High-Resolution Differential Equations

Feb 11, 2019
Bin Shi, Simon S. Du, Weijie J. Su, Michael I. Jordan


  Access Model/Code and Paper
Width Provably Matters in Optimization for Deep Linear Neural Networks

Jan 26, 2019
Simon S. Du, Wei Hu


  Access Model/Code and Paper
Provably efficient RL with Rich Observations via Latent State Decoding

Jan 25, 2019
Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford


  Access Model/Code and Paper
Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

Jan 24, 2019
Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruosong Wang


  Access Model/Code and Paper
Gradient Descent Finds Global Minima of Deep Neural Networks

Nov 30, 2018
Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai


  Access Model/Code and Paper