11 papers
On the Strong Duality in Continuous-time and Discrete-time Linear Quadratic Regulators
Yuto Watanabe, Yang Zheng
This paper revisits the strong duality in the linear quadratic regulator (LQR) for continuous-time and discrete-time systems, and explores its interconnection with typical assumpti…
Online Nonstochastic Prediction: Logarithmic Regret via Predictive Online Least Squares
Chih-Fan Pai, Yang Zheng
We study online prediction for marginally stable, partially observed linear dynamical systems under nonstochastic disturbances. Our objective is to minimize the cumulative squared…
Regularization in Data-driven Predictive Control: A Convex Relaxation Perspective
Xu Shang, Yang Zheng
This paper explores the role of regularization in data-driven predictive control (DDPC) through the lens of convex relaxation. Using a bi-level optimization framework, we model sys…
Online Tracking with Predictions for Nonlinear Systems with Koopman Linear Embedding
Chih-Fan Pai, Xu Shang, Jiachen Qian +1
We study the problem of online tracking in unknown nonlinear dynamical systems, where only short-horizon predictions of future target states are available. This setting arises in p…
Regret Guarantees for Model-Free Cooperative Filtering under Asynchronous Observations
Jiachen Qian, Yang Zheng
Predicting the output of a dynamical system from streaming data is fundamental to real-time feedback control and decision-making. We first derive an autoregressive representation t…
Gradient Dominance in the Linear Quadratic Regulator: A Unified Analysis for Continuous-Time and Discrete-Time Systems
Yuto Watanabe, Yang Zheng
Despite its nonconvexity, policy optimization for the Linear Quadratic Regulator (LQR) admits a favorable structural property known as gradient dominance, which facilitates linear…