Input-to-State Stability of a Bilevel Proximal Gradient Descent Algorithm

TL;DR

This paper analyzes the convergence and robustness of an interconnected proximal gradient algorithm for bilevel optimization, using input-to-state stability to ensure solutions converge to the optimum in control-aware design contexts.

Contribution

It introduces a control-theoretic approach to analyze the stability of bilevel proximal gradient algorithms, providing new conditions for convergence.

Findings

Proposed an interconnected proximal gradient scheme for bilevel problems.

Derived input-to-state stability conditions ensuring convergence.

Validated robustness of the algorithm in control-aware design applications.

Abstract

This paper studies convergence properties of inexact iterative solution schemes for bilevel optimization problems. Bilevel optimization problems emerge in control-aware design optimization, where the system design parameters are optimized in the outer loop and a discrete-time control trajectory is optimized in the inner loop, but also arise in other domains including machine learning. In the paper an interconnection of proximal gradient algorithms is proposed to solve the inner loop and outer loop optimization problems in the setting of control-aware design optimization and robustness is analyzed from a control-theoretic perspective. By employing input-to-state stability arguments, conditions are derived that ensure convergence of the interconnected scheme to the optimal solution for a class of the bilevel optimization problem.