14
4
v1v2v3 (latest)

Convergence rate of the (1+1)-evolution strategy on locally strongly convex functions with lipschitz continuous gradient and their monotonic transformations

Abstract

Evolution strategy (ES) is one of promising classes of algorithms for black-box continuous optimization. Despite its broad successes in applications, theoretical analysis on the speed of its convergence is limited on convex quadratic functions and their monotonic transformation. In this study, an upper bound and a lower bound of the rate of linear convergence of the (1+1)-ES on locally LL-strongly convex functions with UU-Lipschitz continuous gradient are derived as exp(Ωd(LdU))\exp\left(-\Omega_{d\to\infty}\left(\frac{L}{d\cdot U}\right)\right) and exp(1d)\exp\left(-\frac1d\right), respectively. Notably, any prior knowledge on the mathematical properties of the objective function such as Lipschitz constant is not given to the algorithm, whereas the existing analyses of derivative-free optimization algorithms require them.

View on arXiv
Comments on this paper