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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness


May 01, 2022
Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren, Zi Lin, Yeming Wen, Ghassen Jerfel, Zack Nado, Jasper Snoek, Dustin Tran, Balaji Lakshminarayanan

* arXiv admin note: text overlap with arXiv:2006.10108 

   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

Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence


Jun 30, 2021
Ghassen Jerfel, Serena Wang, Clara Fannjiang, Katherine A. Heller, Yian Ma, Michael I. Jordan

* Accepted for the 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021) 

   Access Paper or Ask Questions

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

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning


Jun 07, 2021
Zachary Nado, Neil Band, Mark Collier, Josip Djolonga, Michael W. Dusenberry, Sebastian Farquhar, Angelos Filos, Marton Havasi, Rodolphe Jenatton, Ghassen Jerfel, Jeremiah Liu, Zelda Mariet, Jeremy Nixon, Shreyas Padhy, Jie Ren, Tim G. J. Rudner, Yeming Wen, Florian Wenzel, Kevin Murphy, D. Sculley, Balaji Lakshminarayanan, Jasper Snoek, Yarin Gal, Dustin Tran


   Access Paper or Ask Questions

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

Underspecification Presents Challenges for Credibility in Modern Machine Learning


Nov 06, 2020
Alexander D'Amour, Katherine Heller, Dan Moldovan, Ben Adlam, Babak Alipanahi, Alex Beutel, Christina Chen, Jonathan Deaton, Jacob Eisenstein, Matthew D. Hoffman, Farhad Hormozdiari, Neil Houlsby, Shaobo Hou, Ghassen Jerfel, Alan Karthikesalingam, Mario Lucic, Yian Ma, Cory McLean, Diana Mincu, Akinori Mitani, Andrea Montanari, Zachary Nado, Vivek Natarajan, Christopher Nielson, Thomas F. Osborne, Rajiv Raman, Kim Ramasamy, Rory Sayres, Jessica Schrouff, Martin Seneviratne, Shannon Sequeira, Harini Suresh, Victor Veitch, Max Vladymyrov, Xuezhi Wang, Kellie Webster, Steve Yadlowsky, Taedong Yun, Xiaohua Zhai, D. Sculley


   Access Paper or Ask Questions

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

Combining Ensembles and Data Augmentation can Harm your Calibration


Oct 19, 2020
Yeming Wen, Ghassen Jerfel, Rafael Muller, Michael W. Dusenberry, Jasper Snoek, Balaji Lakshminarayanan, Dustin Tran


   Access Paper or Ask Questions

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

Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors


May 14, 2020
Michael W. Dusenberry, Ghassen Jerfel, Yeming Wen, Yi-an Ma, Jasper Snoek, Katherine Heller, Balaji Lakshminarayanan, Dustin Tran

* Code available at https://github.com/google/edward2 

   Access Paper or Ask Questions

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

Analyzing the Role of Model Uncertainty for Electronic Health Records


Jun 10, 2019
Michael W. Dusenberry, Dustin Tran, Edward Choi, Jonas Kemp, Jeremy Nixon, Ghassen Jerfel, Katherine Heller, Andrew M. Dai

* Presented at the ICML 2019 Workshop on Uncertainty & Robustness in Deep Learning. Code to be open-sourced 

   Access Paper or Ask Questions

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

AdaNet: A Scalable and Flexible Framework for Automatically Learning Ensembles


Apr 30, 2019
Charles Weill, Javier Gonzalvo, Vitaly Kuznetsov, Scott Yang, Scott Yak, Hanna Mazzawi, Eugen Hotaj, Ghassen Jerfel, Vladimir Macko, Ben Adlam, Mehryar Mohri, Corinna Cortes


   Access Paper or Ask Questions

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

Measuring Calibration in Deep Learning


Apr 02, 2019
Jeremy Nixon, Mike Dusenberry, Linchuan Zhang, Ghassen Jerfel, Dustin Tran


   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
>>