Logarithmic regret bound in partially observable linear dynamical systems S Lale, K Azizzadenesheli, B Hassibi, A Anandkumar
Neural Information Processing Systems (NeurIPS), 2020
117 2020 Reinforcement learning with fast stabilization in linear dynamical systems S Lale, K Azizzadenesheli, B Hassibi, A Anandkumar
International Conference on Artificial Intelligence and Statistics, 5354-5390, 2022
89 * 2022 Stochastic mirror descent on overparameterized nonlinear models N Azizan, S Lale, B Hassibi
IEEE Transactions on Neural Networks and Learning Systems 33 (12), 7717-7727, 2021
83 * 2021 Adaptive control and regret minimization in linear quadratic gaussian (lqg) setting S Lale, K Azizzadenesheli, B Hassibi, A Anandkumar
2021 American Control Conference (ACC), 2517-2522, 2021
48 * 2021 Stochastic linear bandits with hidden low rank structure S Lale, K Azizzadenesheli, A Anandkumar, B Hassibi
arXiv preprint arXiv:1901.09490, 2019
30 2019 Model learning predictive control in nonlinear dynamical systems S Lale, K Azizzadenesheli, B Hassibi, A Anandkumar
2021 60th IEEE Conference on Decision and Control (CDC), 757-762, 2021
27 2021 Regret-optimal controller for the full-information problem O Sabag, G Goel, S Lale, B Hassibi
2021 American Control Conference (ACC), 4777-4782, 2021
27 2021 Regret-Optimal LQR Control O Sabag, G Goel, S Lale, B Hassibi
arXiv preprint arXiv:2105.01244, 2021
21 * 2021 Regret minimization in partially observable linear quadratic control S Lale, K Azizzadenesheli, B Hassibi, A Anandkumar
arXiv preprint arXiv:2002.00082, 2020
19 2020 Forecasting subcritical cylinder wakes with Fourier Neural Operators PI Renn, C Wang, S Lale, Z Li, A Anandkumar, M Gharib
arXiv preprint arXiv:2301.08290, 2023
16 2023 Thompson Sampling Achieves T Kargin*, S Lale*, K Azizzadenesheli, A Anandkumar, B Hassibi
Conference on Learning Theory, 3235-3284, 2022
16 2022 KCRL: Krasovskii-constrained reinforcement learning with guaranteed stability in nonlinear discrete-time systems S Lale, Y Shi, G Qu, K Azizzadenesheli, A Wierman, A Anandkumar
2023 62nd IEEE conference on decision and control (CDC), 1334-1341, 2023
13 * 2023 Stable online control of linear time-varying systems G Qu*, Y Shi*, S Lale*, A Anandkumar, A Wierman
Learning for Dynamics and Control, 742-753, 2021
13 2021 Finite-time system identification and adaptive control in autoregressive exogenous systems S Lale, K Azizzadenesheli, B Hassibi, A Anandkumar
Learning for Dynamics and Control, 967-979, 2021
13 2021 A study of generalization of stochastic mirror descent algorithms on overparameterized nonlinear models N Azizan, S Lale, B Hassibi
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
13 2020 Optimal competitive-ratio control O Sabag, S Lale, B Hassibi
arXiv preprint arXiv:2206.01782, 2022
9 2022 Cem-gd: Cross-entropy method with gradient descent planner for model-based reinforcement learning K Huang, S Lale, U Rosolia, Y Shi, A Anandkumar
arXiv preprint arXiv:2112.07746, 2021
8 2021 Thompson sampling for partially observable linear-quadratic control T Kargin, S Lale, K Azizzadenesheli, A Anandkumar, B Hassibi
2023 American Control Conference (ACC), 4561-4568, 2023
6 2023 Stochastic linear bandits with unknown safety constraints and local feedback KN Varma, S Lale, A Anandkumar
ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems, 2023
5 2023 Explicit regularization via regularizer mirror descent N Azizan, S Lale, B Hassibi
arXiv preprint arXiv:2202.10788, 2022
5 * 2022 
Babak HassibiMose and Lilian S. Bohn Professor of Electrical EngineeringEmail được xác minh tại caltech.edu