Robust and structure exploiting optimisation algorithms: an integral quadratic constraint approach
From MaRDI portal
Abstract: We consider the problem of analyzing and designing gradient-based discrete-time optimization algorithms for a class of unconstrained optimization problems having strongly convex objective functions with Lipschitz continuous gradient. By formulating the problem as a robustness analysis problem and making use of a suitable adaptation of the theory of integral quadratic constraints, we establish a framework that allows to analyze convergence rates and robustness properties of existing algorithms and enables the design of novel robust optimization algorithms with prespecified guarantees capable of exploiting additional structure in the objective function.
Recommendations
- Analysis and design of optimization algorithms via integral quadratic constraints
- Analysis of optimization algorithms via integral quadratic constraints: nonstrongly convex problems
- Convex Synthesis of Accelerated Gradient Algorithms
- Design of distributed and robust optimization algorithms. A systems theoretic approach
- Synthesis of accelerated gradient algorithms for optimization and saddle point problems using Lyapunov functions and LMIs
Cites work
- All stability multipliers for repeated MIMO nonlinearities
- Analysis and design of optimization algorithms via integral quadratic constraints
- Analysis of optimization algorithms via integral quadratic constraints: nonstrongly convex problems
- Control Perspectives on Numerical Algorithms and Matrix Problems
- Design of distributed and robust optimization algorithms. A systems theoretic approach
- Efficient first-order methods for convex minimization: a constructive approach
- Exact worst-case performance of first-order methods for composite convex optimization
- scientific article; zbMATH DE number 3513598 (Why is no real title available?)
- scientific article; zbMATH DE number 917233 (Why is no real title available?)
- scientific article; zbMATH DE number 1424229 (Why is no real title available?)
- scientific article; zbMATH DE number 3365044 (Why is no real title available?)
- scientific article; zbMATH DE number 3387195 (Why is no real title available?)
- scientific article; zbMATH DE number 3100566 (Why is no real title available?)
- Introductory lectures on convex optimization. A basic course.
- Machine learning. A probabilistic perspective
- New results for analysis of systems with repeated nonlinearities
- On Stability of Discrete-Time LTI Systems With Varying Time Delays
- Performance of first-order methods for smooth convex minimization: a novel approach
- Relaxed Logarithmic Barrier Function Based Model Predictive Control of Linear Systems
- Robust accelerated gradient methods for smooth strongly convex functions
- Robust stability and performance analysis based on integral quadratic constraints
- Stability Conditions for Systems with Monotone and Slope-Restricted Nonlinearities
- System analysis via integral quadratic constraints
Cited in
(20)- Time-varying Zames-Falb multipliers for LTI systems are superfluous
- A frequency-domain analysis of inexact gradient methods
- Synthesis of accelerated gradient algorithms for optimization and saddle point problems using Lyapunov functions and LMIs
- A robust algorithm for quadratic optimization under quadratic constraints
- Explicit stabilised gradient descent for faster strongly convex optimisation
- Analysis and design of optimization algorithms via integral quadratic constraints
- Analysis of optimization algorithms via integral quadratic constraints: nonstrongly convex problems
- Connections between Georgiou and Smith's robust stability type theorems and the nonlinear small-gain theorems
- Time-varying continuous-time optimisation with pre-defined finite-time stability
- Convex Synthesis of Accelerated Gradient Algorithms
- Zames–Falb multipliers for convergence rate: motivating example and convex searches
- Extending the Scope of Robust Quadratic Optimization
- Design of distributed and robust optimization algorithms. A systems theoretic approach
- A robustification approach in unconstrained quadratic optimization
- On the necessity and sufficiency of discrete-time O'Shea-Zames-Falb multipliers
- Nonlinear optimization filters for stochastic time-varying convex optimization
- Automated tight Lyapunov analysis for first-order methods
- Entropic risk-averse generalized momentum methods
- Multi-objective robust controller synthesis with integral quadratic constraints in discrete-time
- Analysis and synthesis of switched optimization algorithms
This page was built for publication: Robust and structure exploiting optimisation algorithms: an integral quadratic constraint approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5012635)
