A statistical learning theory approach for uncertain linear and bilinear matrix inequalities

DOI10.1016/j.automatica.2014.04.005zbMath1296.93208arXiv1305.4952OpenAlexW2094001563MaRDI QIDQ458858

Qing-Guo Wang, Fabrizio Dabbene, Venkatakrishnan Venkataramanan, Mohammadreza Chamanbaz, Roberto Tempo

Publication date: 8 October 2014

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1305.4952

zbMATH Keywords

randomized algorithmsstatistical learning theoryVapnik-Chervonenkis dimensionprobabilistic designuncertain linear/bilinear matrix inequality

Mathematics Subject Classification ID

Related Items (2)

A statistical learning theory approach for uncertain linear and bilinear matrix inequalities ⋮ Randomized methods for design of uncertain systems: sample complexity and sequential algorithms

Uses Software

• complib
• PENNON
• YALMIP
• COMPleib
• RACT

Cites Work

• Unnamed Item
• Unnamed Item
• A statistical learning theory approach for uncertain linear and bilinear matrix inequalities
• Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
• Polynomial-time algorithms for probabilistic solutions of parameter-dependent linear matrix inequalities
• Reduced vertex set result for interval semidefinite optimization problems
• Uncertain convex programs: randomized solutions and confidence levels
• Robust output-feedback controller design via local BMI optimization
• Global optimization for the biaffine matrix inequality problem
• Research on probabilistic methods for control system design
• Randomized algorithms for analysis and control of uncertain systems. With applications
• A probabilistic analytic center cutting plane method for feasibility of uncertain LMIs
• An ellipsoid algorithm for probabilistic robust controller design
• A new vertex result for robustness problems with interval matrix uncertainty
• On the density of families of sets
• Improved sample complexity estimates for statistical learning control of uncertain systems
• Sequential Randomized Algorithms for Convex Optimization in the Presence of Uncertainty
• The Exact Feasibility of Randomized Solutions of Uncertain Convex Programs
• Semidefinite optimization
• Robust Solutions to Uncertain Semidefinite Programs
• Linear Matrix Inequalities in System and Control Theory
• PENNON: A code for convex nonlinear and semidefinite programming
• Stochastic algorithms for exact and approximate feasibility of robust LMIs
• Semidefinite Programming
• Randomized Strategies for Probabilistic Solutions of Uncertain Feasibility and Optimization Problems
• Probabilistic Robust Controller Design: Probable Near Minimax Value and Randomized Algorithms
• The Scenario Approach to Robust Control Design
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Probabilistic constrained optimization. Methodology and applications
• Probabilistic robust design with linear quadratic regulators
• Randomized algorithms for robust controller synthesis using statistical learning theory
• Probabilistic solutions to some NP-hard matrix problems

This page was built for publication: A statistical learning theory approach for uncertain linear and bilinear matrix inequalities