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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Do Bayesian Neural Networks Need To Be Fully Stochastic?


Nov 11, 2022
Mrinank Sharma, Sebastian Farquhar, Eric Nalisnick, Tom Rainforth

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

Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles


Oct 30, 2022
Rajeev Verma, Daniel Barrejón, Eric Nalisnick

Add code

* First two authors contributed equally 

   Access Paper or Ask Questions

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

Sampling-based inference for large linear models, with application to linearised Laplace


Oct 10, 2022
Javier Antorán, Shreyas Padhy, Riccardo Barbano, Eric Nalisnick, David Janz, José Miguel Hernández-Lobato

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

Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions


Jun 30, 2022
Urja Khurana, Ivar Vermeulen, Eric Nalisnick, Marloes van Noorloos, Antske Fokkens

Add code

* Accepted at WOAH 2022, co-located at NAACL 2022. Cite ACL version 

   Access Paper or Ask Questions

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

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

Add code

* 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

Adversarial Defense via Image Denoising with Chaotic Encryption


Mar 19, 2022
Shi Hu, Eric Nalisnick, Max Welling

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

Calibrated Learning to Defer with One-vs-All Classifiers


Feb 08, 2022
Rajeev Verma, Eric Nalisnick

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

How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task


Nov 18, 2021
Urja Khurana, Eric Nalisnick, Antske Fokkens

Add code

* Accepted at the second workshop on Evaluation & Comparison of NLP Systems, co-located at EMNLP 2021. Cite ACL version 

   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

Add code

* 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

Predictive Complexity Priors


Jul 01, 2020
Eric Nalisnick, Jonathan Gordon, José Miguel Hernández-Lobato

Add code

* 22 pages 

   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
>>