Pavel Izmailov
Artificial Intelligence · 2017–2023
A researcher in the Science corpus: 17 papers; trusts 1,769 researchers and is trusted by 338 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 581 citations into it; #2,632 of 36,961 by trust here, #2,799 by citations
- Computer Vision and Pattern Recognition — 305 citations into it; #3,035 of 21,973 by trust here, #2,666 by citations
- Optimization & Training — 148 citations into it; #708 of 2,605 by trust here, #443 by citations
- Probabilistic & Bayesian Methods — 115 citations into it; #797 of 1,526 by trust here, #443 by citations
- Representation & Self-Supervised Learning — 83 citations into it; #1,515 of 3,156 by trust here, #1,545 by citations
- Safety, Robustness & Interpretability — 76 citations into it; #1,911 of 2,259 by trust here, #1,188 by citations
- Model Architectures — 69 citations into it; #1,711 of 2,288 by trust here, #1,779 by citations
- Evaluation & Benchmarks — 61 citations into it
Whom Pavel Izmailov trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Yoshua Bengio
- Radford M. Neal
- Yann LeCun
- Ilya Sutskever
- Alex Graves
- Max Welling
Who trusts Pavel Izmailov overall
- Andrew Gordon Wilson
- Wesley J. Maddox
- Stanislav Fort
- Mitchell Wortsman
- Sven Gowal
- Sylvestre-Alvise Rebuffi
- Polina Kirichenko
- Ben Athiwaratkun
- Jean Kaddour
- Garrett Wilson
Papers from Pavel Izmailov's perspective
Ordered by how strongly the researchers Pavel Izmailov trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Averaging Weights Leads to Wider Optima and Better Generalization (2018) — 2,084 citations
- Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs (2018) — 951 citations
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average (2018) — 262 citations
- A Simple Baseline for Bayesian Uncertainty in Deep Learning (2019) — 1,004 citations
- Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data (2020) — 396 citations
- Bayesian Deep Learning and a Probabilistic Perspective of Generalization (2020) — 816 citations
- Does Knowledge Distillation Really Work? (2021) — 292 citations
- Improving Consistency-Based Semi-Supervised Learning with Weight Averaging (2018) — 36 citations
- Subspace Inference for Bayesian Deep Learning (2019) — 164 citations
- Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations (2022) — 483 citations
- Why Normalizing Flows Fail to Detect Out-of-Distribution Data (2020) — 362 citations
- Semi-Supervised Learning with Normalizing Flows (2019) — 137 citations
- What Are Bayesian Neural Network Posteriors Really Like? (2021) — 474 citations
- Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train Decomposition (2017) — 69 citations
- Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision (2023) — 504 citations
- Improving Stability in Deep Reinforcement Learning with Weight Averaging (2018)
- Fast Uncertainty Estimates and Bayesian Model Averaging of DNNs (2018)