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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Learning to Noise: Application-Agnostic Data Sharing with Local Differential Privacy


Oct 23, 2020
Alex Mansbridge, Gregory Barbour, Davide Piras, Christopher Frye, Ilya Feige, David Barber


   Access Paper or Ask Questions

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

Explainability for fair machine learning


Oct 14, 2020
Tom Begley, Tobias Schwedes, Christopher Frye, Ilya Feige

* 8 pages, 3 figures, 2 tables, 1 appendix 

   Access Paper or Ask Questions

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

Human-interpretable model explainability on high-dimensional data


Oct 14, 2020
Damien de Mijolla, Christopher Frye, Markus Kunesch, John Mansir, Ilya Feige

* 8 pages, 6 figures, 1 appendix 

   Access Paper or Ask Questions

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

Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders


Oct 07, 2020
Benoit Gaujac, Ilya Feige, David Barber


   Access Paper or Ask Questions

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

Learning disentangled representations with the Wasserstein Autoencoder


Oct 07, 2020
Benoit Gaujac, Ilya Feige, David Barber


   Access Paper or Ask Questions

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

Shapley-based explainability on the data manifold


Jun 01, 2020
Christopher Frye, Damien de Mijolla, Laurence Cowton, Megan Stanley, Ilya Feige

* 8 pages, 5 figures, 2 appendices 

   Access Paper or Ask Questions

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

Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability


Oct 14, 2019
Christopher Frye, Ilya Feige, Colin Rowat

* 14 pages, 4 figures, 2 appendices 

   Access Paper or Ask Questions

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

Parenting: Safe Reinforcement Learning from Human Input


Feb 18, 2019
Christopher Frye, Ilya Feige

* 9 pages, 4 figures, 1 table 

   Access Paper or Ask Questions

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

Invariant-equivariant representation learning for multi-class data


Feb 08, 2019
Ilya Feige

* 8 pages, 5 figures, 2 tables, 2 appendices 

   Access Paper or Ask Questions

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

Improving latent variable descriptiveness with AutoGen


Jun 12, 2018
Alex Mansbridge, Roberto Fierimonte, Ilya Feige, David Barber

* 8 pages, 2 figures, 5 tables 

   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
>>