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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent


Oct 13, 2022
Satyen Kale, Jason D. Lee, Chris De Sa, Ayush Sekhari, Karthik Sridharan


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability


Sep 30, 2022
Alex Damian, Eshaan Nichani, Jason D. Lee

* First two authors contributed equally 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PAC Reinforcement Learning for Predictive State Representations


Jul 15, 2022
Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural Networks can Learn Representations with Gradient Descent


Jun 30, 2022
Alex Damian, Jason D. Lee, Mahdi Soltanolkotabi

* COLT 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings


Jun 24, 2022
Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems


Jun 24, 2022
Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials


Jun 08, 2022
Eshaan Nichani, Yu Bai, Jason D. Lee

* 64 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games


Jun 03, 2022
Wenhao Zhan, Jason D. Lee, Zhuoran Yang


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias


May 18, 2022
Itay Safran, Gal Vardi, Jason D. Lee


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Nearly Minimax Algorithms for Linear Bandits with Shared Representation


Mar 29, 2022
Jiaqi Yang, Qi Lei, Jason D. Lee, Simon S. Du

* 19 pages, 3 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
6
7
>>