51 citations · 131 across the 15 of their papers we have counts for
15 papers
EKGNet: A 10.96μW Fully Analog Neural Network for Intra-Patient Arrhythmia Classification
Benyamin Haghi, Lin Ma, Sahin Lale +2
We present an integrated approach by combining analog computing and deep learning for electrocardiogram (ECG) arrhythmia classification. We propose EKGNet, a hardware-efficient and…
Forecasting subcritical cylinder wakes with Fourier Neural Operators
Peter I Renn, Cong Wang, Sahin Lale +3
We apply Fourier neural operators (FNOs), a state-of-the-art operator learning technique, to forecast the temporal evolution of experimentally measured velocity fields. FNOs are a…
Thompson Sampling Achieves Regret in Linear Quadratic Control
Taylan Kargin, Sahin Lale, Kamyar Azizzadenesheli +2
Thompson Sampling (TS) is an efficient method for decision-making under uncertainty, where an action is sampled from a carefully prescribed distribution which is updated based on t…
Optimal Competitive-Ratio Control
Oron Sabag, Sahin Lale, Babak Hassibi
Inspired by competitive policy designs approaches in online learning, new control paradigms such as competitive-ratio and regret-optimal control have been recently proposed as alte…
KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems
Sahin Lale, Yuanyuan Shi, Guannan Qu +3
Learning a dynamical system requires stabilizing the unknown dynamics to avoid state blow-ups. However, current reinforcement learning (RL) methods lack stabilization guarantees, w…
CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learning
Kevin Huang, Sahin Lale, Ugo Rosolia +2
Current state-of-the-art model-based reinforcement learning algorithms use trajectory sampling methods, such as the Cross-Entropy Method (CEM), for planning in continuous control s…
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…
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…
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…
Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems
Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi +1
In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynamical systems. When learning a dynamical system, one needs to stabilize the unknow…
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-…
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…
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…
Stochastic Mirror Descent on Overparameterized Nonlinear Models: Convergence, Implicit Regularization, and Generalization
Navid Azizan, Sahin Lale, Babak Hassibi
Most modern learning problems are highly overparameterized, meaning that there are many more parameters than the number of training data points, and as a result, the training loss…
Stochastic Linear Bandits with Hidden Low Rank Structure
Sahin Lale, Kamyar Azizzadenesheli, Anima Anandkumar +1
High-dimensional representations often have a lower dimensional underlying structure. This is particularly the case in many decision making settings. For example, when the represen…