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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Adapting the Linearised Laplace Model Evidence for Modern Deep Learning


Jun 17, 2022
Javier Antorán, David Janz, James Urquhart Allingham, Erik Daxberger, Riccardo Barbano, Eric Nalisnick, José Miguel Hernández-Lobato

* Paper appearing 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

Sparse MoEs meet Efficient Ensembles


Oct 07, 2021
James Urquhart Allingham, Florian Wenzel, Zelda E Mariet, Basil Mustafa, Joan Puigcerver, Neil Houlsby, Ghassen Jerfel, Vincent Fortuin, Balaji Lakshminarayanan, Jasper Snoek, Dustin Tran, Carlos Riquelme Ruiz, Rodolphe Jenatton

* 44 pages, 19 figures, 24 tables 

   Access Paper or Ask Questions

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

Expressive yet Tractable Bayesian Deep Learning via Subnetwork Inference


Oct 28, 2020
Erik Daxberger, Eric Nalisnick, James Urquhart Allingham, Javier Antorán, José Miguel Hernández-Lobato

* 15 pages, extended version with supplementary material 

   Access Paper or Ask Questions

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

Depth Uncertainty in Neural Networks


Jun 15, 2020
Javier Antorán, James Urquhart Allingham, José Miguel Hernández-Lobato


   Access Paper or Ask Questions

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

Variational Depth Search in ResNets


Feb 27, 2020
Javier Antorán, James Urquhart Allingham, José Miguel Hernández-Lobato

* Appearing at the 1st ICLR workshop on Neural Architecture Search 2020 

   Access Paper or Ask Questions

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