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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation


Jun 20, 2022
Loucas Pillaud-Vivien, Julien Reygner, Nicolas Flammarion


   Access Paper or Ask Questions

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

Towards Understanding Sharpness-Aware Minimization


Jun 13, 2022
Maksym Andriushchenko, Nicolas Flammarion

* The camera-ready version (accepted at 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

Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs


Jun 02, 2022
Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion


   Access Paper or Ask Questions

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

Accelerated SGD for Non-Strongly-Convex Least Squares


Mar 03, 2022
Aditya Varre, Nicolas Flammarion


   Access Paper or Ask Questions

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

ARIA: Adversarially Robust Image Attribution for Content Provenance


Feb 25, 2022
Maksym Andriushchenko, Xiaoyang Rebecca Li, Geoffrey Oxholm, Thomas Gittings, Tu Bui, Nicolas Flammarion, John Collomosse


   Access Paper or Ask Questions

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

Trace norm regularization for multi-task learning with scarce data


Feb 14, 2022
Etienne Boursier, Mikhail Konobeev, Nicolas Flammarion


   Access Paper or Ask Questions

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

Linear Speedup in Personalized Collaborative Learning


Nov 10, 2021
El Mahdi Chayti, Sai Praneeth Karimireddy, Sebastian U. Stich, Nicolas Flammarion, Martin Jaggi


   Access Paper or Ask Questions

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

Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity


Jun 17, 2021
Scott Pesme, Loucas Pillaud-Vivien, Nicolas Flammarion


   Access Paper or Ask Questions

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

A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip


Jun 10, 2021
Mathieu Even, Raphaƫl Berthier, Francis Bach, Nicolas Flammarion, Pierre Gaillard, Hadrien Hendrikx, Laurent MassouliƩ, Adrien Taylor

* arXiv admin note: substantial text overlap with arXiv:2102.06035 

   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 effectiveness of adversarial training against common corruptions


Mar 03, 2021
Klim Kireev, Maksym Andriushchenko, Nicolas Flammarion


   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
>>