"FALCON: Fourier Adaptive Learning and Control in Partially Observable Nonlinear Dynamical Systems" [Link]
Sahin Lale*, Peter Renn*, Kamyar Azizzadenesheli, Babak Hassibi, Morteza Gharib, Anima Anandkumar (*equal contribution)
Spotlight in NeurIPS 2022 AI for Science Workshop
"Predicting Full-Field Turbulent Flows Using Fourier Neural Operator"
Peter Renn, Sahin Lale, Cong Wang, Zongyi Li, Anima Anandkumar, Morteza Gharib
NeurIPS 2022 Machine Learning and the Physical Sciences Workshop
"Thompson Sampling Achieves O(T) Regret in Linear Quadratic Control [Link]
Taylan Kargin*, Sahin Lale*, Kamyar Azizzadenesheli, Anima Anandkumar, Babak Hassibi (*equal contribution)
Conference on Learning Theory (COLT) 2022
"Optimal Competitive-Ratio Control" [Link]
Oron Sabag, Sahin Lale, Babak Hassibi
Conference on Decision and Control (CDC) 2022
Extended version under review
"Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems" [Link]
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar
International Conference on Artificial Intelligence and Statistics (AISTATS) 2022
"KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems" [Link]
Sahin Lale, Yuanyuan Shi, Guannan Qu, Kamyar Azizzadenesheli, Adam Wierman, Anima Anandkumar
Under Review
"CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learning" [Link]
Kevin Huang, Sahin Lale, Ugo Rosolia, Yuanyuan Shi, Anima Anandkumar
Under Review
"Model Learning Predictive Control in Nonlinear Dynamical Systems"
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar
Conference on Decision and Control (CDC) 2021
"Explicit Regularization via Regularizer Mirror Descent" [Link]
Navid Azizan, Sahin Lale, Babak Hassibi
Spotlight in ICML 2021 Overparameterization: Pitfalls & Opportunities Workshop
Under Review
"Finite-time System Identification and Adaptive Control in ARX Systems" [Link]
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar
Learning for Dynamics and Control (L4DC) 2021
"Stable Online Control of Linear Time-Varying Systems" [Link]
Guannan Qu*, Yuanyuan Shi*, Sahin Lale*, Anima Anandkumar, Adam Wierman (*equal contribution)
Learning for Dynamics and Control (L4DC) 2021
"Stability and Identification of Random Asynchronous Linear Time-Invariant Systems" [Link]
Sahin Lale*, Oguzhan Teke*, Babak Hassibi, Anima Anandkumar (*equal contribution)
Learning for Dynamics and Control (L4DC) 2021
"Regret-Optimal Full-Information Control" [Link]
Oron Sabag, Sahin Lale, Gautam Goel, Babak Hassibi
American Control Conference (ACC) 2021
Extended version under review
"Adaptive Control and Regret Minimization in Linear Quadratic Gaussian (LQG) Setting" [Link]
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar
American Control Conference (ACC) 2021
"Regret Minimization in Partially Observable Linear Quadratic Control" [Link]
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar
NeurIPS 2019 Safety and Robustness in Decision-making Workshop
Under Review
"Stochastic Linear Bandits with Hidden Low Rank Structure" [Link]
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar
NeurIPS 2019 Machine Learning with Guarantees Workshop
Under Review
"A Study of Generalization of Stochastic Mirror Descent Algorithms on Overparameterized Nonlinear Models" [Link]
Navid Azizan, Sahin Lale, Babak Hassibi
2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)