Extended Matrix Cube Theorems with Applications to μ-Theory in Control

Abstract

In this paper, we study semi-infinite systems of Linear Matrix Inequalities which are generically NP-hard. For these systems, we introduce computationally tractable approximations and derive quantitative guarantees of their quality. As applications, we discuss the problem of maximizing a Hermitian quadratic form over the complex unit cube and the problem of bounding the complex structured singular value. With the help of our complex Matrix Cube Theorem we demonstrate that the standard scaling upper bound on μ(M) is a tight upper bound on the largest level of structured perturbations of the matrix M for which all perturbed matrices share a common Lyapunov certificate for the (discrete time) stability.

Keywords

This publication has 10 references indexed in Scilit:

Robust optimization ? methodology and applications
Mathematical Programming, 2002
On Tractable Approximations of Uncertain Linear Matrix Inequalities Affected by Interval Uncertainty
SIAM Journal on Optimization, 2002
Lectures on Modern Convex Optimization
Published by Society for Industrial & Applied Mathematics (SIAM) ,2001
Robustness
Published by Springer Nature ,2000
Robust Convex Optimization
Mathematics of Operations Research, 1998
Robust Solutions to Uncertain Semidefinite Programs
SIAM Journal on Optimization, 1998
Robust Solutions to Least-Squares Problems with Uncertain Data
SIAM Journal on Matrix Analysis and Applications, 1997
Linear Matrix Inequalities in System and Control Theory
Published by Society for Industrial & Applied Mathematics (SIAM) ,1994
Interior-Point Polynomial Algorithms in Convex Programming
Published by Society for Industrial & Applied Mathematics (SIAM) ,1994
The complex structured singular value
Automatica, 1993