Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Jason D. Lee

Provable Hierarchy-Based Meta-Reinforcement Learning


Oct 18, 2021
Kurtland Chua, Qi Lei, Jason D. Lee


  Access Paper or Ask Questions

Provable Regret Bounds for Deep Online Learning and Control


Oct 15, 2021
Xinyi Chen, Edgar Minasyan, Jason D. Lee, Elad Hazan


  Access Paper or Ask Questions

Towards General Function Approximation in Zero-Sum Markov Games


Jul 30, 2021
Baihe Huang, Jason D. Lee, Zhaoran Wang, Zhuoran Yang


  Access Paper or Ask Questions

Going Beyond Linear RL: Sample Efficient Neural Function Approximation


Jul 14, 2021
Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang


  Access Paper or Ask Questions

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization


Jul 09, 2021
Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang


  Access Paper or Ask Questions

A Short Note on the Relationship of Information Gain and Eluder Dimension


Jul 06, 2021
Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei


  Access Paper or Ask Questions

Near-Optimal Linear Regression under Distribution Shift


Jun 23, 2021
Qi Lei, Wei Hu, Jason D. Lee

* ICML 2021 

  Access Paper or Ask Questions

Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence


May 24, 2021
Wenhao Zhan, Shicong Cen, Baihe Huang, Yuxin Chen, Jason D. Lee, Yuejie Chi


  Access Paper or Ask Questions

How Fine-Tuning Allows for Effective Meta-Learning


May 05, 2021
Kurtland Chua, Qi Lei, Jason D. Lee


  Access Paper or Ask Questions

Bilinear Classes: A Structural Framework for Provable Generalization in RL


Mar 19, 2021
Simon S. Du, Sham M. Kakade, Jason D. Lee, Shachar Lovett, Gaurav Mahajan, Wen Sun, Ruosong Wang


  Access Paper or Ask Questions

MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning


Feb 23, 2021
DiJia Su, Jason D. Lee, John M. Mulvey, H. Vincent Poor


  Access Paper or Ask Questions

A Theory of Label Propagation for Subpopulation Shift


Feb 22, 2021
Tianle Cai, Ruiqi Gao, Jason D. Lee, Qi Lei


  Access Paper or Ask Questions

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


Feb 17, 2021
Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du


  Access Paper or Ask Questions

Beyond Lazy Training for Over-parameterized Tensor Decomposition


Oct 22, 2020
Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge

* NeurIPS 2020; the first two authors contribute equally 

  Access Paper or Ask Questions

Provable Benefits of Representation Learning in Linear Bandits


Oct 13, 2020
Jiaqi Yang, Wei Hu, Jason D. Lee, Simon S. Du

* 28 pages, 6 figures 

  Access Paper or Ask Questions

How Important is the Train-Validation Split in Meta-Learning?


Oct 12, 2020
Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, Caiming Xiong


  Access Paper or Ask Questions

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot


Sep 22, 2020
Jingtong Su, Yihang Chen, Tianle Cai, Tianhao Wu, Ruiqi Gao, Liwei Wang, Jason D. Lee

* Original submission to NeurIPS 2020. Under review 

  Access Paper or Ask Questions

Generalized Leverage Score Sampling for Neural Networks


Sep 21, 2020
Jason D. Lee, Ruoqi Shen, Zhao Song, Mengdi Wang, Zheng Yu


  Access Paper or Ask Questions

Predicting What You Already Know Helps: Provable Self-Supervised Learning


Aug 03, 2020
Jason D. Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo


  Access Paper or Ask Questions

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy


Jul 13, 2020
Edward Moroshko, Suriya Gunasekar, Blake Woodworth, Jason D. Lee, Nathan Srebro, Daniel Soudry


  Access Paper or Ask Questions

Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks


Jul 03, 2020
Cong Fang, Jason D. Lee, Pengkun Yang, Tong Zhang


  Access Paper or Ask Questions

Towards Understanding Hierarchical Learning: Benefits of Neural Representations


Jun 24, 2020
Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher


  Access Paper or Ask Questions

Shape Matters: Understanding the Implicit Bias of the Noise Covariance


Jun 18, 2020
Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma


  Access Paper or Ask Questions

Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters


Jun 16, 2020
Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor

* 28 pages, 8 figures, 2 tables 

  Access Paper or Ask Questions

Distributed Estimation for Principal Component Analysis: a Gap-free Approach


Apr 05, 2020
Xi Chen, Jason D. Lee, He Li, Yun Yang


  Access Paper or Ask Questions

Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting


Mar 23, 2020
Lemeng Wu, Mao Ye, Qi Lei, Jason D. Lee, Qiang Liu


  Access Paper or Ask Questions

Kernel and Rich Regimes in Overparametrized Models


Feb 24, 2020
Blake Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro

* This updates and significantly extends a previous article (arXiv:1906.05827), Sections 6 and 7.1 are the most major additions. 30 pages. arXiv admin note: text overlap with arXiv:1906.05827 

  Access Paper or Ask Questions

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 Paper or Ask Questions

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 Paper or Ask Questions

When Does Non-Orthogonal Tensor Decomposition Have No Spurious Local Minima?


Nov 22, 2019
Maziar Sanjabi, Sina Baharlouei, Meisam Razaviyayn, Jason D. Lee


  Access Paper or Ask Questions