Pavel Izmailov

According to our database, Pavel Izmailov authored at least 27 papers between 2016 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Can a Confident Prior Replace a Cold Posterior?

Martin Marek, Brooks Paige, Pavel Izmailov

CoRR, 2024

Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision.

Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, Jeffrey Wu

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Simple and Fast Group Robustness by Automatic Feature Reweighting.

Shikai Qiu, Andres Potapczynski, Pavel Izmailov, Andrew Gordon Wilson

Proceedings of the International Conference on Machine Learning, 2023

Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations.

Polina Kirichenko, Pavel Izmailov, Andrew Gordon Wilson

Proceedings of the Eleventh International Conference on Learning Representations, 2023

FlexiViT: One Model for All Patch Sizes.

Lucas Beyer, Pavel Izmailov, Alexander Kolesnikov, Mathilde Caron, Simon Kornblith, Xiaohua Zhai, Matthias Minderer, Michael Tschannen, Ibrahim Alabdulmohsin, Filip Pavetic

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification.

Sanyam Kapoor, Wesley J. Maddox, Pavel Izmailov, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

On Feature Learning in the Presence of Spurious Correlations.

Pavel Izmailov, Polina Kirichenko, Nate Gruver, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Bayesian Model Selection, the Marginal Likelihood, and Generalization.

Sanae Lotfi, Pavel Izmailov, Gregory W. Benton, Micah Goldblum, Andrew Gordon Wilson

Proceedings of the International Conference on Machine Learning, 2022

2021

Evaluating Approximate Inference in Bayesian Deep Learning.

Andrew Gordon Wilson, Pavel Izmailov, Matthew D. Hoffman, Yarin Gal, Yingzhen Li, Melanie F. Pradier, Sharad Vikram, Andrew Y. K. Foong, Sanae Lotfi, Sebastian Farquhar

Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, 2021

Does Knowledge Distillation Really Work?

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

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Dangers of Bayesian Model Averaging under Covariate Shift.

Pavel Izmailov, Patrick Nicholson, Sanae Lotfi, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

What Are Bayesian Neural Network Posteriors Really Like?

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

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Tensor Train Decomposition on TensorFlow (T3F).

Alexander Novikov, Pavel Izmailov, Valentin Khrulkov, Michael Figurnov, Ivan V. Oseledets

J. Mach. Learn. Res., 2020

Learning Invariances in Neural Networks.

Gregory W. Benton, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson

CoRR, 2020

Bayesian Deep Learning and a Probabilistic Perspective of Generalization.

Andrew Gordon Wilson, Pavel Izmailov

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

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

Polina Kirichenko, Pavel Izmailov, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Learning Invariances in Neural Networks from Training Data.

Gregory W. Benton, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Semi-Supervised Learning with Normalizing Flows.

Pavel Izmailov, Polina Kirichenko, Marc Finzi, Andrew Gordon Wilson

Proceedings of the 37th International Conference on Machine Learning, 2020

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

Marc Finzi, Samuel Stanton, Pavel Izmailov, Andrew Gordon Wilson

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

Subspace Inference for Bayesian Deep Learning.

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

Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, 2019

A Simple Baseline for Bayesian Uncertainty in Deep Learning.

Wesley J. Maddox, Pavel Izmailov, Timur Garipov, Dmitry P. Vetrov, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average.

Ben Athiwaratkun, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

Improving Consistency-Based Semi-Supervised Learning with Weight Averaging.

Ben Athiwaratkun, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson

CoRR, 2018

Averaging Weights Leads to Wider Optima and Better Generalization.

Pavel Izmailov, Dmitrii Podoprikhin, Timur Garipov, Dmitry P. Vetrov, Andrew Gordon Wilson

Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, 2018

Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs.

Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry P. Vetrov, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

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

Pavel Izmailov, Alexander Novikov, Dmitry Kropotov

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2016

Faster variational inducing input Gaussian process classification.

Pavel Izmailov, Dmitry Kropotov

CoRR, 2016