Pavel Izmailov

1. From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence
   2026/01/06 by Marc Finzi, Shikai Qiu, Yiding Jiang +3 · 13 voices · 9 citations
   #cs.LG #stat.ML
2. Averaging Weights Leads to Wider Optima and Better Generalization
   2018/03/14 by Pavel Izmailov, Izmailov, Pavel, D. A. Podoprikhin +7 · 129 citations
   Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
3. Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
   2018/02/27 by Timur Garipov, Garipov, Timur, Pavel Izmailov +7 · 69 citations
   Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #Adversarial Robustness in Machine Learning
4. A Simple Baseline for Bayesian Uncertainty in Deep Learning
   2019/02/07 by Wesley J. Maddox, Maddox, Wesley, Timur Garipov +7 · 81 citations
   Computer Science · #Gaussian Processes and Bayesian Inference #Adversarial Robustness in Machine Learning #Domain Adaptation and Few-Shot Learning
5. Bayesian Deep Learning and a Probabilistic Perspective of Generalization
   2020/02/20 by Andrew Gordon Wilson, Wilson, Andrew Gordon, Pavel Izmailov +1 · 33 citations
   Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification
6. Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
   2022/04/06 by Polina Kirichenko, Pavel Izmailov, Kirichenko, Polina +3 · 38 citations
   Computer Science · #AI in cancer detection #Generative Adversarial Networks and Image Synthesis #Machine Learning and Data Classification
7. Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
   2023/12/14 by Collin Burns, Burns, Collin, Pavel Izmailov +21 · 52 citations
   Computer Science · #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
8. What Are Bayesian Neural Network Posteriors Really Like?
   2021/04/29 by Pavel Izmailov, Izmailov, Pavel, Sharad Vikram +5 · 22 citations
   Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Markov Chains and Monte Carlo Methods
9. FlexiViT: One Model for All Patch Sizes
   2022/12/15 by Lucas Beyer, Pavel Izmailov, Beyer, Lucas +17 · 27 citations
   Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #Advanced Image and Video Retrieval Techniques
10. Generalizing Convolutional Neural Networks for Equivariance to Lie\n Groups on Arbitrary Continuous Data
    2020/02/25 by Marc Finzi, Finzi, Marc, Samuel Stanton +6 · 25 citations
    Computer Science · Biochemistry, Genetics and Molecular Biology · Materials Science · #Computational Physics and Python Applications #Protein Structure and Dynamics #Machine Learning in Materials Science
11. Why Normalizing Flows Fail to Detect Out-of-Distribution Data
    2020/06/15 by Polina Kirichenko, Kirichenko, Polina, Pavel Izmailov +3 · 19 citations
    Computer Science · #Anomaly Detection Techniques and Applications #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML)
12. Does Knowledge Distillation Really Work?
    2021/06/10 by Samuel Stanton, Pavel Izmailov, Stanton, Samuel +7 · 19 citations
    Computer Science · Physics and Astronomy · #Domain Adaptation and Few-Shot Learning #Adversarial Robustness in Machine Learning #Model Reduction and Neural Networks
13. On Feature Learning in the Presence of Spurious Correlations
    2022/10/20 by Pavel Izmailov, Polina Kirichenko, Izmailov, Pavel +5 · 21 citations
    Engineering · Computer Science · #Industrial Vision Systems and Defect Detection #Face and Expression Recognition #Image Enhancement Techniques
14. Subspace Inference for Bayesian Deep Learning
    2019/07/17 by Pavel Izmailov, Wesley J. Maddox, Izmailov, Pavel +9 · 9 citations
    Computer Science · #Gaussian Processes and Bayesian Inference #Anomaly Detection Techniques and Applications #Generative Adversarial Networks and Image Synthesis
15. Bayesian Model Selection, the Marginal Likelihood, and Generalization
    2022/02/23 by Sanae Lotfi, Lotfi, Sanae, Pavel Izmailov +7 · 8 citations
    Computer Science · #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification
16. Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train Decomposition
    2017/10/19 by Pavel Izmailov, Alexander Novikov, Izmailov, Pavel +3 · 2 citations
    Computer Science · Mathematics · Physics and Astronomy · #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Scientific Research and Discoveries #Tensor decomposition and applications
17. Learning Invariances in Neural Networks
    2020/10/22 by Gregory W. Benton, Marc Finzi, Benton, Gregory +5 · 2 citations
    Computer Science · Materials Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science #Neural Networks and Applications
18. Understanding Reasoning from Pretraining to Post-Training
    2026/07/17 by Jingyan Shen, Ang Li, Salman Rahman +4 · 1 voice
    #cs.LG #cs.AI #cs.CL