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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains


Dec 01, 2022
Kefan Dong, Tengyu Ma

Add code

* added citations and fixed typos 

   Access Paper or Ask Questions

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

What learning algorithm is in-context learning? Investigations with linear models


Nov 29, 2022
Ekin Akyürek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, Denny Zhou

Add code

* fix url in the abstract 

   Access Paper or Ask Questions

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

A Theoretical Study of Inductive Biases in Contrastive Learning


Nov 27, 2022
Jeff Z. HaoChen, Tengyu Ma

Add code


   Access Paper or Ask Questions

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

How Does Sharpness-Aware Minimization Minimize Sharpness?


Nov 10, 2022
Kaiyue Wen, Tengyu Ma, Zhiyuan Li

Add code

* 81 pages, 1 figure 

   Access Paper or Ask Questions

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

Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models


Oct 25, 2022
Hong Liu, Sang Michael Xie, Zhiyuan Li, Tengyu Ma

Add code


   Access Paper or Ask Questions

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

Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift


Jul 18, 2022
Ananya Kumar, Tengyu Ma, Percy Liang, Aditi Raghunathan

Add code

* Accepted to UAI 2022 

   Access Paper or Ask Questions

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

Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence


Jun 16, 2022
Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma

Add code


   Access Paper or Ask Questions

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

Asymptotic Instance-Optimal Algorithms for Interactive Decision Making


Jun 06, 2022
Kefan Dong, Tengyu Ma

Add code

* 52 pages 

   Access Paper or Ask Questions

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

Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path


May 22, 2022
Haoyuan Cai, Tengyu Ma, Simon Du

Add code

* ICML 2022 

   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
>>