activity
20192021
most citedStochastic Mirror Descent on Overparameterized Nonlinear Models: Convergence, Implicit Regularization, and Generalization

29 citations · 44 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG2021

Finite-time System Identification and Adaptive Control in Autoregressive Exogenous Systems

Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi +1

Autoregressive exogenous (ARX) systems are the general class of input-output dynamical systems used for modeling stochastic linear dynamical systems (LDS) including partially obser…

math.OC2021

Stable Online Control of Linear Time-Varying Systems

Guannan Qu, Yuanyuan Shi, Sahin Lale +2

Linear time-varying (LTV) systems are widely used for modeling real-world dynamical systems due to their generality and simplicity. Providing stability guarantees for LTV systems i…

cs.LG20201 cited

Stability and Identification of Random Asynchronous Linear Time-Invariant Systems

Sahin Lale, Oguzhan Teke, Babak Hassibi +1

In many computational tasks and dynamical systems, asynchrony and randomization are naturally present and have been considered as ways to increase the speed and reduce the cost of…

cs.LG2020

Regret Minimization in Partially Observable Linear Quadratic Control

Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi +1

We study the problem of regret minimization in partially observable linear quadratic control systems when the model dynamics are unknown a priori. We propose ExpCommit, an explore-…

cs.LG2020

Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems

Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi +1

We study the problem of system identification and adaptive control in partially observable linear dynamical systems. Adaptive and closed-loop system identification is a challenging…

cs.LG2020

Adaptive Control and Regret Minimization in Linear Quadratic Gaussian (LQG) Setting

Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi +1

We study the problem of adaptive control in partially observable linear quadratic Gaussian control systems, where the model dynamics are unknown a priori. We propose LqgOpt, a nove…