| Averaging Weights Leads to Wider Optima and Better Generalization P Izmailov, D Podoprikhin, T Garipov, D Vetrov, AG Wilson Uncertainty in Artificial Intelligence (UAI), 2018 | 952 | 2018 |
| A Simple Baseline for Bayesian Uncertainty in Deep Learning W Maddox, T Garipov, P Izmailov, D Vetrov, AG Wilson Advances in Neural Information Processing Systems (NeurIPS), 2019 | 552 | 2019 |
| Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs T Garipov, P Izmailov, D Podoprikhin, DP Vetrov, AG Wilson Advances in Neural Information Processing Systems (NeurIPS), 2018 | 449 | 2018 |
| Bayesian Deep Learning and a Probabilistic Perspective of Generalization AG Wilson, P Izmailov Advances in Neural Information Processing Systems (NeurIPS), 2020 | 364 | 2020 |
| There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average B Athiwaratkun, M Finzi, P Izmailov, AG Wilson International Conference on Learning Representations (ICLR 2019), 2018 | 243* | 2018 |
| Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data M Finzi, S Stanton, P Izmailov, AG Wilson International Conference on Machine Learning (ICML), 2020 | 182 | 2020 |
| What Are Bayesian Neural Network Posteriors Really Like? P Izmailov, S Vikram, MD Hoffman, AG Wilson International Conference on Machine Learning (ICML), 2021 | 173 | 2021 |
| Why Normalizing Flows Fail to Detect Out-of-Distribution Data P Kirichenko, P Izmailov, AG Wilson Advances in Neural Information Processing Systems (NeurIPS), 2020 | 124 | 2020 |
| Subspace Inference for Bayesian Deep Learning P Izmailov, WJ Maddox, P Kirichenko, T Garipov, D Vetrov, AG Wilson Uncertainty in Artificial Intelligence (UAI), 2019 | 105 | 2019 |
| Learning Invariances in Neural Networks G Benton, M Finzi, P Izmailov, AG Wilson Advances in Neural Information Processing Systems (NeurIPS), 2020 | 86* | 2020 |
| Does Knowledge Distillation Really Work? S Stanton, P Izmailov, P Kirichenko, AA Alemi, AG Wilson Advances in Neural Information Processing Systems (NeurIPS), 2021 | 75 | 2021 |
| Semi-Supervised Learning with Normalizing Flows P Izmailov, P Kirichenko, M Finzi, AG Wilson International Conference on Machine Learning (ICML), 2019 | 72 | 2019 |
| Tensor Train decomposition on TensorFlow (T3F) A Novikov, P Izmailov, V Khrulkov, M Figurnov, I Oseledets Journal of Machine Learning Research 21, 2020 | 54 | 2020 |
| Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train Decomposition P Izmailov, A Novikov, D Kropotov Artificial Intelligence and Statistics (AISTATS), 2018 | 51 | 2018 |
| Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations P Kirichenko, P Izmailov, AG Wilson International Conference on Learning Representations (ICLR 2023), 2022 | 47 | 2022 |
| Improving Stability in Deep Reinforcement Learning with Weight Averaging E Nikishin, P Izmailov, B Athiwaratkun, D Podoprikhin, T Garipov, ... Uncertainty in Deep Learning Workshop at UAI, 2018 | 27 | 2018 |
| Dangers of Bayesian Model Averaging under Covariate Shift P Izmailov, P Nicholson, S Lotfi, AG Wilson Advances in Neural Information Processing Systems (NeurIPS), 2021 | 21 | 2021 |
| Bayesian Model Selection, the Marginal Likelihood, and Generalization S Lotfi, P Izmailov, G Benton, M Goldblum, AG Wilson International Conference on Machine Learning (ICML), 2022 | 16 | 2022 |
| Invertible Convolutional Networks M Finzi, P Izmailov, W Maddox, P Kirichenko, AG Wilson Workshop on Invertible Neural Nets and Normalizing Flows at ICML, 2019 | 12 | 2019 |
| On Feature Learning in the Presence of Spurious Correlations P Izmailov, P Kirichenko, N Gruver, AG Wilson Advances in Neural Information Processing Systems (NeurIPS), 2022 | 10 | 2022 |
Andrew Gordon WilsonNew York UniversityVerified email at cims.nyu.edu
