650 citations · 1.3k across the 33 of their papers we have counts for
11 papers · 1 filter
Bounds for the Tracking Error and Dynamic Regret of Inexact Online Optimization Methods: A General Analysis via Sequential Semidefinite Programs
Usman Syed, Emiliano Dall'Anese, Bin Hu
In this paper, we develop a unified framework for analyzing the tracking error and dynamic regret of inexact online optimization methods under a variety of settings. Specifically,…
Learning the Kalman Filter with Fine-Grained Sample Complexity
Xiangyuan Zhang, Bin Hu, Tamer Başar
We develop the first end-to-end sample complexity of model-free policy gradient (PG) methods in discrete-time infinite-horizon Kalman filtering. Specifically, we introduce the rece…
Global Convergence of Direct Policy Search for State-Feedback Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential
Xingang Guo, Bin Hu
Direct policy search has been widely applied in modern reinforcement learning and continuous control. However, the theoretical properties of direct policy search on nonsmooth robus…
Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies
Bin Hu, Kaiqing Zhang, Na Li +3
Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical…
Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Łojasiewicz Functions when the Non-Convexity is Averaged-Out
Jun-Kun Wang, Chi-Heng Lin, Andre Wibisono +1
Heavy Ball (HB) nowadays is one of the most popular momentum methods in non-convex optimization. It has been widely observed that incorporating the Heavy Ball dynamic in gradient-b…
Connectivity of the Feasible and Sublevel Sets of Dynamic Output Feedback Control with Robustness Constraints
Bin Hu, Yang Zheng
This paper considers the optimization landscape of linear dynamic output feedback control with robustness constraints. We consider the feasible set of all the…
Convex Programs and Lyapunov Functions for Reinforcement Learning: A Unified Perspective on the Analysis of Value-Based Methods
Xingang Guo, Bin Hu
Value-based methods play a fundamental role in Markov decision processes (MDPs) and reinforcement learning (RL). In this paper, we present a unified control-theoretic framework for…
On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions
Aaron Havens, Bin Hu
When applying imitation learning techniques to fit a policy from expert demonstrations, one can take advantage of prior stability/robustness assumptions on the expert's policy and…
Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs
Bin Hu, Stephen Wright, Laurent Lessard
Techniques for reducing the variance of gradient estimates used in stochastic programming algorithms for convex finite-sum problems have received a great deal of attention in recen…
A Robust Accelerated Optimization Algorithm for Strongly Convex Functions
Saman Cyrus, Bin Hu, Bryan Van Scoy +1
This work proposes an accelerated first-order algorithm we call the Robust Momentum Method for optimizing smooth strongly convex functions. The algorithm has a single scalar parame…
Dissipativity Theory for Nesterov's Accelerated Method
Bin Hu, Laurent Lessard
In this paper, we adapt the control theoretic concept of dissipativity theory to provide a natural understanding of Nesterov's accelerated method. Our theory ties rigorous converge…