GLOBAL LINEAR CONVERGENCE OF EVOLUTION STRATEGIES ON MORE THAN SMOOTH STRONGLY CONVEX FUNCTIONS

GLOBAL LINEAR CONVERGENCE OF EVOLUTION STRATEGIES ON MORE THAN SMOOTH STRONGLY CONVEX FUNCTIONS

Evolution strategies (ESs) are zeroth-order stochastic black-box optimization heuristics invariant to monotonic transformations of the objective function. They evolve a multivariate normal distribution, from which candidate solutions are generated. Among different variants, CMA-ES is nowadays recogn...

Full description

Bibliographic Details
Main Authors: Akimoto, Y. (Author), Auger, A. (Author), Glasmachers, T. (Author), Morinaga, D. (Author)
Format: Article
Language:English
Published: Society for Industrial and Applied Mathematics Publications 2022
Subjects:
black-box optimization
Black-box optimization
Convex functions
Covariance matrix
Derivative-free optimization
evolution strategies
Evolution strategies
Evolutionary algorithms
Functions
linear convergence
Linear convergence
Monotonic transformation
Normal distribution
Number theory
Optimization
Optimization heuristics
randomized derivative free optimization
Randomized derivative free optimization
stochastic algorithms
Stochastic algorithms
Stochastic systems
Stochastics
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items