| Gradient descent only converges to minimizers JD Lee, M Simchowitz, MI Jordan, B Recht Conference on learning theory, 1246-1257, 2016 | 891* | 2016 |
| Delayed impact of fair machine learning LT Liu, S Dean, E Rolf, M Simchowitz, M Hardt International Conference on Machine Learning, 3150-3158, 2018 | 547 | 2018 |
| Low-rank solutions of linear matrix equations via procrustes flow S Tu, R Boczar, M Simchowitz, M Soltanolkotabi, B Recht International Conference on Machine Learning, 964-973, 2016 | 428 | 2016 |
| Learning without mixing: Towards a sharp analysis of linear system identification M Simchowitz, H Mania, S Tu, MI Jordan, B Recht Conference On Learning Theory, 439-473, 2018 | 376 | 2018 |
| First-order methods almost always avoid strict saddle points JD Lee, I Panageas, G Piliouras, M Simchowitz, MI Jordan, B Recht Mathematical programming 176, 311-337, 2019 | 364 | 2019 |
| Reward-free exploration for reinforcement learning C Jin, A Krishnamurthy, M Simchowitz, T Yu International Conference on Machine Learning, 4870-4879, 2020 | 246 | 2020 |
| Naive exploration is optimal for online lqr M Simchowitz, D Foster International Conference on Machine Learning, 8937-8948, 2020 | 210 | 2020 |
| Non-asymptotic gap-dependent regret bounds for tabular mdps M Simchowitz, KG Jamieson Advances in Neural Information Processing Systems 32, 2019 | 175 | 2019 |
| Improper learning for non-stochastic control M Simchowitz, K Singh, E Hazan Conference on Learning Theory, 3320-3436, 2020 | 156 | 2020 |
| Learning linear dynamical systems with semi-parametric least squares M Simchowitz, R Boczar, B Recht Conference on Learning Theory, 2714-2802, 2019 | 140 | 2019 |
| Corruption-robust exploration in episodic reinforcement learning T Lykouris, M Simchowitz, A Slivkins, W Sun Conference on Learning Theory, 3242-3245, 2021 | 124 | 2021 |
| The implicit fairness criterion of unconstrained learning LT Liu, M Simchowitz, M Hardt International Conference on Machine Learning, 4051-4060, 2019 | 89 | 2019 |
| Do differentiable simulators give better policy gradients? HJ Suh, M Simchowitz, K Zhang, R Tedrake International Conference on Machine Learning, 20668-20696, 2022 | 85 | 2022 |
| Logarithmic regret for adversarial online control D Foster, M Simchowitz International Conference on Machine Learning, 3211-3221, 2020 | 78 | 2020 |
| The simulator: Understanding adaptive sampling in the moderate-confidence regime M Simchowitz, K Jamieson, B Recht Conference on Learning Theory, 1794-1834, 2017 | 76 | 2017 |
| Reward-free rl is no harder than reward-aware rl in linear markov decision processes AJ Wagenmaker, Y Chen, M Simchowitz, S Du, K Jamieson International Conference on Machine Learning, 22430-22456, 2022 | 61 | 2022 |
| Constrained episodic reinforcement learning in concave-convex and knapsack settings K Brantley, M Dudik, T Lykouris, S Miryoosefi, M Simchowitz, A Slivkins, ... Advances in Neural Information Processing Systems 33, 16315-16326, 2020 | 57 | 2020 |
| Bayesian decision-making under misspecified priors with applications to meta-learning M Simchowitz, C Tosh, A Krishnamurthy, DJ Hsu, T Lykouris, M Dudik, ... Advances in Neural Information Processing Systems 34, 26382-26394, 2021 | 56 | 2021 |
| Approximate ranking from pairwise comparisons R Heckel, M Simchowitz, K Ramchandran, M Wainwright International Conference on Artificial Intelligence and Statistics, 1057-1066, 2018 | 51 | 2018 |
| Learning the linear quadratic regulator from nonlinear observations Z Mhammedi, DJ Foster, M Simchowitz, D Misra, W Sun, A Krishnamurthy, ... Advances in Neural Information Processing Systems 33, 14532-14543, 2020 | 49 | 2020 |
Benjamin RechtProfessor of EECS, University of California, BerkeleyVerified email at eecs.berkeley.edu
