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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks


Oct 28, 2022
Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna


   Access Paper or Ask Questions

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

Learning Single-Index Models with Shallow Neural Networks


Oct 27, 2022
Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song

* 76 pages. To appear at NeurIPS 2022 

   Access Paper or Ask Questions

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

Towards Antisymmetric Neural Ansatz Separation


Aug 05, 2022
Aaron Zweig, Joan Bruna


   Access Paper or Ask Questions

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

On Non-Linear operators for Geometric Deep Learning


Jul 06, 2022
Grégoire Sergeant-Perthuis, Jakob Maier, Joan Bruna, Edouard Oyallon


   Access Paper or Ask Questions

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

On Gradient Descent Convergence beyond the Edge of Stability


Jun 08, 2022
Lei Chen, Joan Bruna


   Access Paper or Ask Questions

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

Exponential Separations in Symmetric Neural Networks


Jun 02, 2022
Aaron Zweig, Joan Bruna


   Access Paper or Ask Questions

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

When does return-conditioned supervised learning work for offline reinforcement learning?


Jun 02, 2022
David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna


   Access Paper or Ask Questions

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

On Feature Learning in Neural Networks with Global Convergence Guarantees


Apr 22, 2022
Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna

* Accepted by the 10th International Conference on Learning Representations (ICLR 2022) 

   Access Paper or Ask Questions

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

Neural Galerkin Scheme with Active Learning for High-Dimensional Evolution Equations


Mar 02, 2022
Joan Bruna, Benjamin Peherstorfer, Eric Vanden-Eijnden


   Access Paper or Ask Questions

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

Simultaneous Transport Evolution for Minimax Equilibria on Measures


Feb 21, 2022
Carles Domingo-Enrich, Joan Bruna

* Error in the proof of Lemma 1, which makes Theorem 1 not hold 

   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
>>