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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model

Jul 09, 2019
Guodong Zhang, Lala Li, Zachary Nado, James Martens, Sushant Sachdeva, George E. Dahl, Christopher J. Shallue, Roger Grosse


  Access Paper or Ask Questions

Adversarial Robustness through Local Linearization

Jul 04, 2019
Chongli Qin, James Martens, Sven Gowal, Dilip Krishnan, Krishnamurthy, Dvijotham, Alhussein Fawzi, Soham De, Robert Stanforth, Pushmeet Kohli


  Access Paper or Ask Questions

Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks

May 27, 2019
Guodong Zhang, James Martens, Roger Grosse


  Access Paper or Ask Questions

Differentiable Game Mechanics

May 13, 2019
Alistair Letcher, David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster, Karl Tuyls, Thore Graepel

* Journal of Machine Learning Research (JMLR), v20 (84) 1-40, 2019 
* JMLR 2019, journal version of arXiv:1802.05642 

  Access Paper or Ask Questions

On the Variance of Unbiased Online Recurrent Optimization

Feb 06, 2019
Tim Cooijmans, James Martens


  Access Paper or Ask Questions

The Mechanics of n-Player Differentiable Games

Jun 06, 2018
David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster, Karl Tuyls, Thore Graepel

* PMLR volume 80, 2018 
* ICML 2018, final version 

  Access Paper or Ask Questions

New insights and perspectives on the natural gradient method

Nov 21, 2017
James Martens

* Many small revisions/corrections throughout , Added a section on 2nd-order methods and future work 

  Access Paper or Ask Questions

A Kronecker-factored approximate Fisher matrix for convolution layers

May 23, 2016
Roger Grosse, James Martens


  Access Paper or Ask Questions

Optimizing Neural Networks with Kronecker-factored Approximate Curvature

May 04, 2016
James Martens, Roger Grosse

* Various minor additions, corrections and tweaks. Added link to code 

  Access Paper or Ask Questions

Adding Gradient Noise Improves Learning for Very Deep Networks

Nov 21, 2015
Arvind Neelakantan, Luke Vilnis, Quoc V. Le, Ilya Sutskever, Lukasz Kaiser, Karol Kurach, James Martens


  Access Paper or Ask Questions

On the Expressive Efficiency of Sum Product Networks

Jan 23, 2015
James Martens, Venkatesh Medabalimi

* Various minor revisions and corrections throughout 

  Access Paper or Ask Questions

Estimating the Hessian by Back-propagating Curvature

Sep 04, 2012
James Martens, Ilya Sutskever, Kevin Swersky

* Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012) 

  Access Paper or Ask Questions