| The computational limits of deep learning NC Thompson, K Greenewald, K Lee, GF Manso arXiv preprint arXiv:2007.05558 10, 2, 2020 | 1371* | 2020 |
| Bayesian nonparametric federated learning of neural networks M Yurochkin, M Agarwal, S Ghosh, K Greenewald, N Hoang, Y Khazaeni International conference on machine learning, 7252-7261, 2019 | 1056 | 2019 |
| Personalized heartsteps: A reinforcement learning algorithm for optimizing physical activity P Liao, K Greenewald, P Klasnja, S Murphy Proceedings of the ACM on interactive, mobile, wearable and ubiquitous …, 2020 | 261 | 2020 |
| Estimating information flow in deep neural networks Z Goldfeld, E Berg, K Greenewald, I Melnyk, N Nguyen, B Kingsbury, ... arXiv preprint arXiv:1810.05728, 2018 | 235 | 2018 |
| Identifiability guarantees for causal disentanglement from soft interventions J Zhang, K Greenewald, C Squires, A Srivastava, K Shanmugam, C Uhler Advances in Neural Information Processing Systems 36, 50254-50292, 2023 | 121 | 2023 |
| Convergence of smoothed empirical measures with applications to entropy estimation Z Goldfeld, K Greenewald, J Niles-Weed, Y Polyanskiy IEEE Transactions on Information Theory 66 (7), 4368-4391, 2020 | 108 | 2020 |
| Asymmetry in low-rank adapters of foundation models J Zhu, K Greenewald, K Nadjahi, HSDO Borde, RB Gabrielsson, ... arXiv preprint arXiv:2402.16842, 2024 | 81 | 2024 |
| Sliced mutual information: A scalable measure of statistical dependence Z Goldfeld, K Greenewald Advances in Neural Information Processing Systems 34, 17567-17578, 2021 | 74 | 2021 |
| Action centered contextual bandits K Greenewald, A Tewari, S Murphy, P Klasnja Advances in neural information processing systems 30, 2017 | 68 | 2017 |
| Tensor graphical lasso (TeraLasso) K Greenewald, S Zhou, A Hero III Journal of the Royal Statistical Society Series B: Statistical Methodology …, 2019 | 62 | 2019 |
| Sample efficient active learning of causal trees K Greenewald, D Katz, K Shanmugam, S Magliacane, M Kocaoglu, ... Advances in Neural Information Processing Systems 32, 2019 | 56 | 2019 |
| Gaussian-smoothed optimal transport: Metric structure and statistical efficiency Z Goldfeld, K Greenewald International Conference on Artificial Intelligence and Statistics, 3327-3337, 2020 | 52 | 2020 |
| Robust kronecker product PCA for spatio-temporal covariance estimation K Greenewald, AO Hero IEEE Transactions on Signal Processing 63 (23), 6368-6378, 2015 | 51 | 2015 |
| Statistical model aggregation via parameter matching M Yurochkin, M Agarwal, S Ghosh, K Greenewald, N Hoang Advances in neural information processing systems 32, 2019 | 46 | 2019 |
| Active structure learning of causal DAGs via directed clique trees C Squires, S Magliacane, K Greenewald, D Katz, M Kocaoglu, ... Advances in Neural Information Processing Systems 33, 21500-21511, 2020 | 45 | 2020 |
| Measuring generalization with optimal transport CY Chuang, Y Mroueh, K Greenewald, A Torralba, S Jegelka Advances in neural information processing systems 34, 8294-8306, 2021 | 41 | 2021 |
| Score distillation via reparametrized ddim A Lukoianov, H Sáez de Ocáriz Borde, K Greenewald, V Guizilini, ... Advances in Neural Information Processing Systems 37, 26011-26044, 2024 | 38 | 2024 |
| Ensemble estimation of information divergence KR Moon, K Sricharan, K Greenewald, AO Hero III Entropy 20 (8), 560, 2018 | 36 | 2018 |
| Improving convergence of divergence functional ensemble estimators KR Moon, K Sricharan, K Greenewald, AO Hero 2016 IEEE International Symposium on Information Theory (ISIT), 1133-1137, 2016 | 35 | 2016 |
| Distributional preference alignment of llms via optimal transport I Melnyk, Y Mroueh, B Belgodere, M Rigotti, A Nitsure, M Yurochkin, ... Advances in Neural Information Processing Systems 37, 104412-104442, 2024 | 32 | 2024 |
Mikhail YurochkinStaff AI Scientist, IFM MBZUAI, ex MIT-IBM Watson AI LabVerified email at umich.edu
