Pavel Izmailov

Contact: pi390@nyu.edu, Twitter
Iām a PhD student in Computer Science at NYU, working with Andrew Gordon Wilson. In my research, I aim to build foundational understanding of models, training procedures, and their limitations. I use this understanding to develop practically impactful, interpretable, robust and broadly applicable methods and models. My interests include out of distribution generalization, probabilistic deep learning, representation learning, large models, and other topics. Our work on Bayesian model selection was recently recognized with an Outstanding Paper Award š at ICML 2022!
In years 2017ā2019 I was a PhD student in Operations Research and Information Engineering at Cornell University, after which I received an MSc degree and transferred to NYU. I received a BSc in applied math and computer science from the faculty of Computational Mathematics and Cybernetics of Lomonosov Moscow State University, where I was working at the Bayesian Methods Research Group under supervision of Dmitry Vetrov and Dmitry Kropotov.
In the summer of 2019 I completed a research internship at Amazon AWS in Palo Alto, working with Bernie Wang and Alex Smola. In the summer of 2020 I worked with Matt Hoffman at Google AI. Between June 2021 and February 2022 I worked with Alex Alemi and Ben Poole at Google as a research intern and a student researcher. In the summer of 2022 I worked with Lucas Beyer and Simon Kornblith at Google Brain.
I am on the academic job market!
Links
- [Home, Publications, Talks, CV, GitHub, Google Scholar, Semantic Scholar]
Selected Papers
-
*Equal first authorship. Full list of papers available here.
-
FlexiViT: one model for all patch sizes
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[PDF, ArXiv, Code] -
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
International Conference on Learning Representations (ICLR), 2023 š Spotlight Presentation
[PDF, ArXiv, Code] -
On Feature Learning in the Presence of Spurious Correlations
Neural Information Processing Systems (NeurIPS), 2022
[PDF, ArXiv, Code] -
Bayesian Model Selection, the Marginal Likelihood, and Generalization
International Conference on Machine Learning (ICML), 2022
š Outstanding Paper Award, š¢ Long Talk (Oral)
[PDF, ArXiv, Code] -
Dangers of Bayesian Model Averaging under Covariate Shift
Neural Information Processing Systems (NeurIPS), 2021
[PDF, ArXiv, Poster, Code] -
What Are Bayesian Neural Network Posteriors Really Like?
International Conference on Machine Learning (ICML), 2021
š¢ Long Talk (Oral)
[PDF, ArXiv, Code, HMC samples, Poster, NeurIPS competition] -
Why Normalizing Flows Fail to Detect Out-of-Distribution Data
Neural Information Processing Systems (NeurIPS), 2020
[PDF, ArXiv, Code] -
Bayesian Deep Learning and a Probabilistic Perspective of Generalization
Neural Information Processing Systems (NeurIPS), 2020
[PDF, ArXiv, Code] -
A Simple Baseline for Bayesian Uncertainty in Deep Learning
Neural Information Processing Systems (NeurIPS), 2019
[PDF, ArXiv, Code, Poster, Video] -
Averaging Weights Leads to Wider Optima and Better Generalization
Uncertainty in Artificial Intelligence (UAI), 2018
š¢ Oral Presentation
[PDF, ArXiv, Code, Poster, Slides, PyTorch Blogpost, Towards Data Science Blogpost, fast.ai Blogpost] -
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Neural Information Processing Systems (NeurIPS), 2018
š Spotlight Presentation
[PDF, ArXiv, Code, Poster, Slides, Video, Blogpost]