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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Aspects of scaling and scalability for flow-based sampling of lattice QCD


Nov 14, 2022
Ryan Abbott, Michael S. Albergo, Aleksandar Botev, Denis Boyda, Kyle Cranmer, Daniel C. Hackett, Alexander G. D. G. Matthews, Sébastien Racanière, Ali Razavi, Danilo J. Rezende, Fernando Romero-López, Phiala E. Shanahan, Julian M. Urban

Add code

* 22 pages, 8 figures 

   Access Paper or Ask Questions

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

Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers


Mar 15, 2022
Guodong Zhang, Aleksandar Botev, James Martens

Add code

* 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

SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision


Nov 10, 2021
Irina Higgins, Peter Wirnsberger, Andrew Jaegle, Aleksandar Botev

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

Which priors matter? Benchmarking models for learning latent dynamics


Nov 09, 2021
Aleksandar Botev, Andrew Jaegle, Peter Wirnsberger, Daniel Hennes, Irina Higgins

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

Better, Faster Fermionic Neural Networks


Nov 13, 2020
James S. Spencer, David Pfau, Aleksandar Botev, W. M. C. Foulkes

Add code

* To appear at the 3rd NeurIPS Workshop on Machine Learning and Physical Science 

   Access Paper or Ask Questions

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

Disentangling by Subspace Diffusion


Jun 23, 2020
David Pfau, Irina Higgins, Aleksandar Botev, Sébastien Racanière

Add code

* 21 pages, 13 figures 

   Access Paper or Ask Questions

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

Hamiltonian Generative Networks


Sep 30, 2019
Peter Toth, Danilo Jimenez Rezende, Andrew Jaegle, Sébastien Racanière, Aleksandar Botev, Irina Higgins

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

Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting


May 20, 2018
Hippolyt Ritter, Aleksandar Botev, David Barber

Add code

* 13 pages, 6 figures 

   Access Paper or Ask Questions

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

Practical Gauss-Newton Optimisation for Deep Learning


Jun 13, 2017
Aleksandar Botev, Hippolyt Ritter, David Barber

Add code

* ICML 2017 

   Access Paper or Ask Questions

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

Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent


Jul 11, 2016
Aleksandar Botev, Guy Lever, David Barber

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
1
2
>>