| Policy Optimization for Linear Control with Robustness Guarantee: Implicit Regularization and Global Convergence K Zhang, B Hu, T Başar SIAM Journal on Control and Optimization 59 (6), 4081-4109, 2021 | 163* | 2021 |
| Dissipativity Theory for Nesterov's Accelerated Method B Hu, L Lessard International Conference on Machine Learning (ICML), 1549-1557, 2017 | 131 | 2017 |
| A robust accelerated optimization algorithm for strongly convex functions S Cyrus, B Hu, B Van Scoy, L Lessard 2018 Annual American Control Conference (ACC), 1376-1381, 2018 | 81 | 2018 |
| Characterizing the exact behaviors of temporal difference learning algorithms using Markov jump linear system theory B Hu, U Syed Advances in Neural Information Processing Systems, 8479-8490, 2019 | 64 | 2019 |
| Analysis of biased stochastic gradient descent using sequential semidefinite programs B Hu, P Seiler, L Lessard Mathematical Programming 187, 383-408, 2020 | 61 | 2020 |
| Toward a Theoretical Foundation of Policy Optimization for Learning Control Policies B Hu, K Zhang, N Li, M Mesbahi, M Fazel, T Başar Annual Review of Control, Robotics, and Autonomous Systems 6, 123-158, 2023 | 60 | 2023 |
| On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems K Zhang, B Hu, T Basar Advances in Neural Information Processing Systems 33, 22056-22068, 2020 | 56 | 2020 |
| Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity K Zhang, X Zhang, B Hu, T Basar Advances in Neural Information Processing Systems 34, 2949-2964, 2021 | 53* | 2021 |
| Control interpretations for first-order optimization methods B Hu, L Lessard 2017 American Control Conference (ACC), 3114-3119, 2017 | 48 | 2017 |
| Exponential decay rate conditions for uncertain linear systems using integral quadratic constraints B Hu, P Seiler IEEE Transactions on Automatic Control 61 (11), 3631-3637, 2016 | 46 | 2016 |
| Robust convergence analysis of distributed optimization algorithms A Sundararajan, B Hu, L Lessard 2017 55th Annual Allerton Conference on Communication, Control, and …, 2017 | 45 | 2017 |
| Convergence guarantees of policy optimization methods for markovian jump linear systems JP Jansch-Porto, B Hu, GE Dullerud 2020 American Control Conference (ACC), 2882-2887, 2020 | 39 | 2020 |
| A unified analysis of stochastic optimization methods using jump system theory and quadratic constraints B Hu, P Seiler, A Rantzer Conference on Learning Theory (COLT), 1157-1189, 2017 | 37 | 2017 |
| A Unified Algebraic Perspective on Lipschitz Neural Networks A Araujo, AJ Havens, B Delattre, A Allauzen, B Hu International Conference on Learning Representations, 2023 | 35 | 2023 |
| Robustness analysis of uncertain discrete‐time systems with dissipation inequalities and integral quadratic constraints B Hu, MJ Lacerda, P Seiler International Journal of Robust and Nonlinear Control 27 (11), 1940-1962, 2017 | 30 | 2017 |
| Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs B Hu, S Wright, L Lessard International Conference on Machine Learning (ICML), 2038-2047, 2018 | 28 | 2018 |
| Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability H Xue, A Araujo, B Hu, Y Chen Thirty-seventh Conference on Neural Information Processing Systems, 2023 | 23 | 2023 |
| Policy Learning of MDPs with Mixed Continuous/Discrete Variables: A Case Study on Model-Free Control of Markovian Jump Systems JP Jansch-Porto, B Hu, G Dullerud Learning for Dynamics and Control, 947-957, 2020 | 21 | 2020 |
| Pivotal decomposition for reliability analysis of fault tolerant control systems on unmanned aerial vehicles B Hu, P Seiler Reliability Engineering & System Safety 140, 130-141, 2015 | 19 | 2015 |
| Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out JK Wang, CH Lin, A Wibisono, B Hu International Conference on Machine Learning, 22839-22864, 2022 | 18 | 2022 |
Peter Seiler JrUniversity of Michigan, Ann Arbor在 umich.edu 的电子邮件经过验证
