Pavel Izmailov

2.6k total citations · 1 hit paper
11 papers, 514 citations indexed

About

Pavel Izmailov is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Geochemistry and Petrology. According to data from OpenAlex, Pavel Izmailov has authored 11 papers receiving a total of 514 indexed citations (citations by other indexed papers that have themselves been cited), including 10 papers in Artificial Intelligence, 6 papers in Computer Vision and Pattern Recognition and 1 paper in Geochemistry and Petrology. Recurrent topics in Pavel Izmailov's work include Advanced Neural Network Applications (5 papers), Domain Adaptation and Few-Shot Learning (5 papers) and Adversarial Robustness in Machine Learning (3 papers). Pavel Izmailov is often cited by papers focused on Advanced Neural Network Applications (5 papers), Domain Adaptation and Few-Shot Learning (5 papers) and Adversarial Robustness in Machine Learning (3 papers). Pavel Izmailov collaborates with scholars based in United States, Russia and France. Pavel Izmailov's co-authors include Andrew Gordon Wilson, Dmitry Vetrov, Timur Garipov, D. A. Podoprikhin, Marc Finzi, Ben Athiwaratkun, Mathilde Caron, Michael Tschannen, Lucas Beyer and Xiaohua Zhai and has published in prestigious journals such as arXiv (Cornell University), Neural Information Processing Systems and International Conference on Machine Learning.

In The Last Decade

Pavel Izmailov

11 papers receiving 481 citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

Averaging Weights Leads to Wider Optima and Better Generalization

2018 329 citations Pavel Izmailov, D. A. Podoprikhin et al. profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Pavel Izmailov United States	8	333	248	44	30	29	11	514
Yuguang Yan China	16	506 1.5×	290 1.2×	37 0.8×	36 1.2×	37 1.3×	38	718
Timur Garipov Russia	4	260 0.8×	179 0.7×	23 0.5×	24 0.8×	22 0.8×	9	391
Defang Chen China	12	483 1.5×	397 1.6×	29 0.7×	27 0.9×	32 1.1×	26	732
Yooju Shin South Korea	4	382 1.1×	162 0.7×	36 0.8×	29 1.0×	43 1.5×	9	605
D. A. Podoprikhin Russia	6	242 0.7×	176 0.7×	23 0.5×	23 0.8×	22 0.8×	11	411
Gautier Izacard France	4	220 0.7×	244 1.0×	64 1.5×	44 1.5×	22 0.8×	6	497
Devansh Arpit United States	8	336 1.0×	219 0.9×	23 0.5×	12 0.4×	32 1.1×	13	488
Shizhe Hu China	14	325 1.0×	373 1.5×	22 0.5×	28 0.9×	31 1.1×	35	614

Countries citing papers authored by Pavel Izmailov

Since Specialization

Citations

This map shows the geographic impact of Pavel Izmailov's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Pavel Izmailov with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Pavel Izmailov more than expected).

Fields of papers citing papers by Pavel Izmailov

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Pavel Izmailov. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Pavel Izmailov. The network helps show where Pavel Izmailov may publish in the future.

Co-authorship network of co-authors of Pavel Izmailov

This figure shows the co-authorship network connecting the top 25 collaborators of Pavel Izmailov. A scholar is included among the top collaborators of Pavel Izmailov based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Pavel Izmailov. Pavel Izmailov is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

11 of 11 papers shown

1.

Beyer, Lucas, Pavel Izmailov, А. И. Колесников, et al.. (2023). FlexiViT: One Model for All Patch Sizes. 14496–14506. 43 indexed citations

2.

Izmailov, Pavel, Sharad Vikram, Matthew D. Hoffman, & Andrew Gordon Wilson. (2021). What Are Bayesian Neural Network Posteriors Really Like. International Conference on Machine Learning. 4629–4640. 3 indexed citations

3.

Finzi, Marc, et al.. (2020). Learning Invariances in Neural Networks from Training Data.. Neural Information Processing Systems. 33. 17605–17616. 7 indexed citations

4.

Finzi, Marc, et al.. (2020). Generalizing Convolutional Networks for Equivariance to Lie Groups on Arbitrary Continuous Data.. 1 indexed citations

5.

Izmailov, Pavel, et al.. (2020). Semi-Supervised Learning with Normalizing Flows. 1. 4615–4630. 11 indexed citations

6.

Izmailov, Pavel, et al.. (2019). Subspace Inference for Bayesian Deep Learning. 1169–1179. 16 indexed citations

7.

Athiwaratkun, Ben, Marc Finzi, Pavel Izmailov, & Andrew Gordon Wilson. (2018). Improving Consistency-Based Semi-Supervised Learning with Weight Averaging.. arXiv (Cornell University). 7 indexed citations

8.

Athiwaratkun, Ben, Marc Finzi, Pavel Izmailov, & Andrew Gordon Wilson. (2018). There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average. arXiv (Cornell University). 55 indexed citations

9.

Izmailov, Pavel, D. A. Podoprikhin, Timur Garipov, Dmitry Vetrov, & Andrew Gordon Wilson. (2018). Averaging Weights Leads to Wider Optima and Better Generalization. 876–885. 329 indexed citations breakdown →

10.

Garipov, Timur, Pavel Izmailov, D. A. Podoprikhin, Dmitry Vetrov, & Andrew Gordon Wilson. (2018). Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs. 31. 8789–8798. 38 indexed citations

11.

Izmailov, Pavel, et al.. (2017). Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train Decomposition. International Conference on Artificial Intelligence and Statistics. 726–735. 4 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Breakdown of academic impact, for papers by Yuguang Yan Breakdown of academic impact, for papers by Timur Garipov Breakdown of academic impact, for papers by Defang Chen Breakdown of academic impact, for papers by Yooju Shin Breakdown of academic impact, for papers by D. A. Podoprikhin Breakdown of academic impact, for papers by Gautier Izacard Breakdown of academic impact, for papers by Devansh Arpit Breakdown of academic impact, for papers by Shizhe Hu