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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Knowledge Distillation: Bad Models Can Be Good Role Models


Mar 28, 2022
Gal Kaplun, Eran Malach, Preetum Nakkiran, Shai Shalev-Shwartz


   Access Paper or Ask Questions

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

Deconstructing Distributions: A Pointwise Framework of Learning


Feb 20, 2022
Gal Kaplun, Nikhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran

* GK and NG 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

For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functions


Mar 11, 2021
Nishanth Dikkala, Gal Kaplun, Rina Panigrahy


   Access Paper or Ask Questions

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

For self-supervised learning, Rationality implies generalization, provably


Oct 16, 2020
Yamini Bansal, Gal Kaplun, Boaz Barak


   Access Paper or Ask Questions

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

Robustness from Simple Classifiers


Feb 21, 2020
Sharon Qian, Dimitris Kalimeris, Gal Kaplun, Yaron Singer


   Access Paper or Ask Questions

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

Deep Double Descent: Where Bigger Models and More Data Hurt


Dec 04, 2019
Preetum Nakkiran, Gal Kaplun, Yamini Bansal, Tristan Yang, Boaz Barak, Ilya Sutskever

* G.K. and Y.B. 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

SGD on Neural Networks Learns Functions of Increasing Complexity


May 28, 2019
Preetum Nakkiran, Gal Kaplun, Dimitris Kalimeris, Tristan Yang, Benjamin L. Edelman, Fred Zhang, Boaz Barak

* Submitted to NeurIPS 2019 

   Access Paper or Ask Questions

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

Robust Influence Maximization for Hyperparametric Models


Mar 09, 2019
Dimitris Kalimeris, Gal Kaplun, Yaron Singer


   Access Paper or Ask Questions

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