Global Linear Convergence of Evolution Strategies on More than Smooth Strongly Convex Functions

DOI10.1137/20M1373815MaRDI QIDQ5081786

Tobias Glasmachers, Anne Auger, Youhei Akimoto, Daiki Morinaga

Publication date: 17 June 2022

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2009.08647

zbMATH Keywords

linear convergencestochastic algorithmsevolution strategiesblack-box optimizationrandomized derivative free optimization

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Convex programming (90C25) Nonconvex programming, global optimization (90C26) Derivative-free methods and methods using generalized derivatives (90C56) Approximation methods and heuristics in mathematical programming (90C59)

Related Items (1)

Global linear convergence of evolution strategies with recombination on scaling-invariant functions

Uses Software

• MultiMin
• OrthoMADS

Cites Work

• Unnamed Item
• Unnamed Item
• Variable metric random pursuit
• Globally convergent evolution strategies
• Lectures on convex optimization
• Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
• A study of drift analysis for estimating computation time of evolutionary algorithms
• Learning probability distributions in continuous evolutionary algorithms -- a comparative review
• Adaptive drift analysis
• Multiplicative drift analysis
• CMA-ES-based structural topology optimization using a level set boundary expression -- application to optical and carpet cloaks
• Algorithmic analysis of a basic evolutionary algorithm for continuous optimization
• Derivative-free optimization: a review of algorithms and comparison of software implementations
• How the (1+1) ES using isotropic mutations minimizes positive definite quadratic forms
• Optimization of Convex Functions with Random Pursuit
• Convergence of Trust-Region Methods Based on Probabilistic Models
• Drift Analysis and Evolutionary Algorithms Revisited
• Linear Convergence of Comparison-based Step-size Adaptive Randomized Search via Stability of Markov Chains
• OrthoMADS: A Deterministic MADS Instance with Orthogonal Directions
• Introduction to Derivative-Free Optimization
• Theoretical analysis of local search strategies to optimize network communication subject to preserving the total number of links
• Hitting-time and occupation-time bounds implied by drift analysis with applications
• Complexity and global rates of trust-region methods based on probabilistic models
• Bounds on absorption times of directionally biased random sequences
• Generalized drift analysis in continuous domain
• A Stochastic Line Search Method with Expected Complexity Analysis
• Derivative-free optimization methods
• Mesh Adaptive Direct Search Algorithms for Constrained Optimization
• Direct Search Based on Probabilistic Descent
• On a Strong Law of Large Numbers for Martingales
• Foundations of Genetic Algorithms
• Drift analysis and average time complexity of evolutionary algorithms

This page was built for publication: Global Linear Convergence of Evolution Strategies on More than Smooth Strongly Convex Functions