| Lipschitz recurrent neural networks NB Erichson, O Azencot, A Queiruga, L Hodgkinson, MW Mahoney arXiv preprint arXiv:2006.12070, 2020 | 121 | 2020 |
| Multiplicative noise and heavy tails in stochastic optimization L Hodgkinson, M Mahoney International Conference on Machine Learning, 4262-4274, 2021 | 79 | 2021 |
| Noisy recurrent neural networks SH Lim, NB Erichson, L Hodgkinson, MW Mahoney Advances in Neural Information Processing Systems 34, 5124-5137, 2021 | 53 | 2021 |
| Stochastic continuous normalizing flows: training SDEs as ODEs L Hodgkinson, C van der Heide, F Roosta, MW Mahoney Uncertainty in Artificial Intelligence, 1130-1140, 2021 | 37* | 2021 |
| The reproducing Stein kernel approach for post-hoc corrected sampling L Hodgkinson, R Salomone, F Roosta arXiv preprint arXiv:2001.09266, 2020 | 32 | 2020 |
| Taxonomizing local versus global structure in neural network loss landscapes Y Yang, L Hodgkinson, R Theisen, J Zou, JE Gonzalez, K Ramchandran, ... Advances in Neural Information Processing Systems 34, 18722-18733, 2021 | 30 | 2021 |
| Generalization bounds using lower tail exponents in stochastic optimizers L Hodgkinson, U Simsekli, R Khanna, M Mahoney International Conference on Machine Learning, 8774-8795, 2022 | 28* | 2022 |
| Test accuracy vs. generalization gap: Model selection in nlp without accessing training or testing data Y Yang, R Theisen, L Hodgkinson, JE Gonzalez, K Ramchandran, ... Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and …, 2023 | 25* | 2023 |
| Stateful ODE-nets using basis function expansions A Queiruga, NB Erichson, L Hodgkinson, MW Mahoney Advances in Neural Information Processing Systems 34, 21770-21781, 2021 | 13 | 2021 |
| Implicit Langevin algorithms for sampling from log-concave densities L Hodgkinson, R Salomone, F Roosta Journal of Machine Learning Research 22 (136), 1-30, 2021 | 13 | 2021 |
| Fat–tailed variational inference with anisotropic tail adaptive flows F Liang, M Mahoney, L Hodgkinson International Conference on Machine Learning, 13257-13270, 2022 | 12 | 2022 |
| Shadow manifold hamiltonian monte carlo C van der Heide, F Roosta, L Hodgkinson, D Kroese International Conference on Artificial Intelligence and Statistics, 1477-1485, 2021 | 9 | 2021 |
| When are ensembles really effective? R Theisen, H Kim, Y Yang, L Hodgkinson, MW Mahoney Advances in Neural Information Processing Systems 36, 2024 | 8 | 2024 |
| Normal approximations for discrete-time occupancy processes L Hodgkinson, R McVinish, PK Pollett Stochastic Processes and their Applications 130 (10), 6414-6444, 2020 | 8 | 2020 |
| The interpolating information criterion for overparameterized models L Hodgkinson, C van der Heide, R Salomone, F Roosta, MW Mahoney arXiv preprint arXiv:2307.07785, 2023 | 7 | 2023 |
| Monotonicity and double descent in uncertainty estimation with gaussian processes L Hodgkinson, C Van Der Heide, F Roosta, MW Mahoney International Conference on Machine Learning, 13085-13117, 2023 | 7 | 2023 |
| Generalization Guarantees via Algorithm-dependent Rademacher Complexity S Sachs, T van Erven, L Hodgkinson, R Khanna, U ªimºekli The Thirty Sixth Annual Conference on Learning Theory, 4863-4880, 2023 | 5 | 2023 |
| A heavy-tailed algebra for probabilistic programming FT Liang, L Hodgkinson, MW Mahoney Advances in Neural Information Processing Systems 36, 2024 | 4 | 2024 |
| Fast approximate simulation of finite long-range spin systems R McVinish, L Hodgkinson The Annals of Applied Probability 31 (3), 1443-1473, 2021 | 3 | 2021 |
| Compressing deep ode-nets using basis function expansions A Queiruga, NB Erichson, L Hodgkinson, MW Mahoney arXiv preprint arXiv:2106.10820, 2021 | 2 | 2021 |
Michael MahoneyProfessor of Statistics, UC BerkeleyVerified email at stat.berkeley.edu
