| Multi-agent reinforcement learning: A report on challenges and approaches S Kapoor arXiv preprint arXiv:1807.09427, 2018 | 50 | 2018 |
| PAC-Bayes compression bounds so tight that they can explain generalization S Lotfi, M Finzi, S Kapoor, A Potapczynski, M Goldblum, AG Wilson Advances in Neural Information Processing Systems 35, 31459-31473, 2022 | 47 | 2022 |
| Backplay:" man muss immer umkehren" C Resnick, R Raileanu, S Kapoor, A Peysakhovich, K Cho, J Bruna arXiv preprint arXiv:1807.06919, 2018 | 46 | 2018 |
| On uncertainty, tempering, and data augmentation in bayesian classification S Kapoor, WJ Maddox, P Izmailov, AG Wilson Advances in Neural Information Processing Systems 35, 18211-18225, 2022 | 39 | 2022 |
| Pre-train your loss: Easy bayesian transfer learning with informative priors R Shwartz-Ziv, M Goldblum, H Souri, S Kapoor, C Zhu, Y LeCun, ... Advances in Neural Information Processing Systems 35, 27706-27715, 2022 | 38 | 2022 |
| Variational auto-regressive Gaussian processes for continual learning S Kapoor, T Karaletsos, TD Bui International Conference on Machine Learning, 5290-5300, 2021 | 31 | 2021 |
| Large Language Models Must Be Taught to Know What They Don't Know S Kapoor, N Gruver, M Roberts, K Collins, A Pal, U Bhatt, A Weller, ... arXiv preprint arXiv:2406.08391, 2024 | 13* | 2024 |
| Function-space regularization in neural networks: A probabilistic perspective TGJ Rudner, S Kapoor, S Qiu, AG Wilson International Conference on Machine Learning, 29275-29290, 2023 | 13 | 2023 |
| Skiing on simplices: Kernel interpolation on the permutohedral lattice for scalable gaussian processes S Kapoor, M Finzi, KA Wang, AGG Wilson International Conference on Machine Learning, 5279-5289, 2021 | 13 | 2021 |
| When are Iterative Gaussian Processes Reliably Accurate? WJ Maddox, S Kapoor, AG Wilson arXiv preprint arXiv:2112.15246, 2021 | 11 | 2021 |
| Policy gradients in a nutshell S Kapoor Towards Data Science 20, 18, 2018 | 7 | 2018 |
| Should we learn most likely functions or parameters? S Qiu, TGJ Rudner, S Kapoor, AG Wilson Advances in Neural Information Processing Systems 36, 2024 | 6 | 2024 |
| A simple and fast baseline for tuning large XGBoost models S Kapoor, V Perrone arXiv preprint arXiv:2111.06924, 2021 | 6 | 2021 |
| First-order preconditioning via hypergradient descent T Moskovitz, R Wang, J Lan, S Kapoor, T Miconi, J Yosinski, A Rawal arXiv preprint arXiv:1910.08461, 2019 | 6 | 2019 |
Andrew Gordon WilsonNew York UniversityVerified email at cims.nyu.edu
