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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Pavel Izmailov

Does Knowledge Distillation Really Work?


Jun 10, 2021
Samuel Stanton, Pavel Izmailov, Polina Kirichenko, Alexander A. Alemi, Andrew Gordon Wilson


  Access Paper or Ask Questions

What Are Bayesian Neural Network Posteriors Really Like?


Apr 29, 2021
Pavel Izmailov, Sharad Vikram, Matthew D. Hoffman, Andrew Gordon Wilson


  Access Paper or Ask Questions

Learning Invariances in Neural Networks


Oct 22, 2020
Gregory Benton, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson

* NeurIPS 2020. Code available at https://github.com/g-benton/learning-invariances 

  Access Paper or Ask Questions

Why Normalizing Flows Fail to Detect Out-of-Distribution Data


Jun 15, 2020
Polina Kirichenko, Pavel Izmailov, Andrew Gordon Wilson

* Code is available at https://github.com/PolinaKirichenko/flows_ood 

  Access Paper or Ask Questions

Bayesian Deep Learning and a Probabilistic Perspective of Generalization


Mar 17, 2020
Andrew Gordon Wilson, Pavel Izmailov

* 28 pages, 17 figures 

  Access Paper or Ask Questions

Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data


Feb 25, 2020
Marc Finzi, Samuel Stanton, Pavel Izmailov, Andrew Gordon Wilson


  Access Paper or Ask Questions

Semi-Supervised Learning with Normalizing Flows


Dec 30, 2019
Pavel Izmailov, Polina Kirichenko, Marc Finzi, Andrew Gordon Wilson


  Access Paper or Ask Questions

Subspace Inference for Bayesian Deep Learning


Jul 17, 2019
Pavel Izmailov, Wesley J. Maddox, Polina Kirichenko, Timur Garipov, Dmitry Vetrov, Andrew Gordon Wilson

* Published at UAI 2019 

  Access Paper or Ask Questions

A Simple Baseline for Bayesian Uncertainty in Deep Learning


Feb 07, 2019
Wesley Maddox, Timur Garipov, Pavel Izmailov, Dmitry Vetrov, Andrew Gordon Wilson


  Access Paper or Ask Questions

Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs


Oct 30, 2018
Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry Vetrov, Andrew Gordon Wilson

* Appears at Advances in Neural Information Processing Systems (NIPS), 2018 

  Access Paper or Ask Questions

Averaging Weights Leads to Wider Optima and Better Generalization


Aug 08, 2018
Pavel Izmailov, Dmitrii Podoprikhin, Timur Garipov, Dmitry Vetrov, Andrew Gordon Wilson

* Appears at the Conference on Uncertainty in Artificial Intelligence (UAI), 2018 

  Access Paper or Ask Questions

Improving Consistency-Based Semi-Supervised Learning with Weight Averaging


Jun 19, 2018
Ben Athiwaratkun, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson

* Fixed a typo for the direction of inequality for $C(\alpha)$ in 3.2 

  Access Paper or Ask Questions

Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train Decomposition


Jan 17, 2018
Pavel Izmailov, Alexander Novikov, Dmitry Kropotov


  Access Paper or Ask Questions

Faster variational inducing input Gaussian process classification


Nov 18, 2016
Pavel Izmailov, Dmitry Kropotov


  Access Paper or Ask Questions