Convex Synthesis of Accelerated Gradient Algorithms
From MaRDI portal
Abstract: We present a convex solution for the design of generalized accelerated gradient algorithms for strongly convex objective functions with Lipschitz continuous gradients. We utilize integral quadratic constraints and the Youla parameterization from robust control theory to formulate a solution of the algorithm design problem as a convex semi-definite program. We establish explicit formulas for the optimal convergence rates and extend the proposed synthesis solution to extremum control problems.
Recommendations
- Acceleration of conjugate gradient algorithms for unconstrained optimization
- Accelerated methods for nonconvex optimization
- On the asymptotic convergence and acceleration of gradient methods
- Accelerated method of conjugate gradients
- scientific article; zbMATH DE number 4028771
- Fast gradient methods for uniformly convex and weakly smooth problems
- A accelerated hybrid descent algorithm for convex minimization
- Conjugate gradients acceleration of coordinate descent for linear systems
- Accelerated gradient methods for nonconvex nonlinear and stochastic programming
- Accelerating the convergence of subgradient optimisation
Cites work
- A course in \(H_{\infty}\) control theory
- A Flexible Synthesis Framework of Structured Controllers for Networked Systems
- A generalized entropy criterion for Nevanlinna-Pick interpolation with degree constraint
- A linear matrix inequality approach to H∞ control
- A new parametrization of H∞ suboptimal controllers
- A synthesis framework for robust gain-scheduling controllers
- All controllers for the general \({\mathcal H}_ \infty\) control problem: LMI existence conditions and state space formulas
- An interpolation theory approach to \(H^{\infty}\) controller degree bounds
- Analysis and design of optimization algorithms via integral quadratic constraints
- Analysis of optimization algorithms via integral quadratic constraints: nonstrongly convex problems
- Conjugation, interpolation and model-matching in H∞
- Feedback and optimal sensitivity: Model reference transformations, multiplicative seminorms, and approximate inverses
- Gain-Scheduling Control With Dynamic Multipliers by Convex Optimization
- scientific article; zbMATH DE number 1001726 (Why is no real title available?)
- scientific article; zbMATH DE number 4164577 (Why is no real title available?)
- scientific article; zbMATH DE number 3987117 (Why is no real title available?)
- scientific article; zbMATH DE number 3513598 (Why is no real title available?)
- scientific article; zbMATH DE number 1424232 (Why is no real title available?)
- Lectures on convex optimization
- Linear-Convex Optimal Steady-State Control
- LMI-based controller synthesis: a unified formulation and solution
- Matrix Analysis
- Multiobjective output-feedback control via LMI optimization
- On the Kalman-Yakubovich-Popov lemma
- On the oracle complexity of smooth strongly convex minimization
- Robust and structure exploiting optimisation algorithms: an integral quadratic constraint approach
- Robust stability and performance analysis based on integral quadratic constraints
- System analysis via integral quadratic constraints
Cited in
(10)- Synthesis of accelerated gradient algorithms for optimization and saddle point problems using Lyapunov functions and LMIs
- Analysis and design of optimization algorithms via integral quadratic constraints
- CVXGEN: a code generator for embedded convex optimization
- Analysis of optimization algorithms via integral quadratic constraints: nonstrongly convex problems
- Robust and structure exploiting optimisation algorithms: an integral quadratic constraint approach
- Nonlinear optimization filters for stochastic time-varying convex optimization
- Passivity preservation in interconnections of linear cone complementarity systems with state jumps
- Multi-objective robust controller synthesis with integral quadratic constraints in discrete-time
- Accelerating recursive least squares adaptation/learning algorithms using a dynamic adaptation gain
- Analysis and synthesis of switched optimization algorithms
This page was built for publication: Convex Synthesis of Accelerated Gradient Algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5020736)
