ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2209.12467
21
4
v1v2v3 (latest)

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

26 September 2022
Daiki Morinaga
Kazuto Fukuchi
Jun Sakuma
Youhei Akimoto
ArXiv (abs)PDFHTML
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 LLL-strongly convex functions with UUU-Lipschitz continuous gradient are derived as exp⁡(−Ωd→∞(Ld⋅U))\exp\left(-\Omega_{d\to\infty}\left(\frac{L}{d\cdot U}\right)\right)exp(−Ωd→∞​(d⋅UL​)) and exp⁡(−1d)\exp\left(-\frac1d\right)exp(−d1​), 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