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. 2204.05817
8
6

Hard Problems are Easier for Success-based Parameter Control

12 April 2022
Mario Alejandro Hevia Fajardo
Dirk Sudholt
ArXivPDFHTML
Abstract

Recent works showed that simple success-based rules for self-adjusting parameters in evolutionary algorithms (EAs) can match or outperform the best fixed parameters on discrete problems. Non-elitism in a (1,λ\lambdaλ) EA combined with a self-adjusting offspring population size λ\lambdaλ outperforms common EAs on the multimodal Cliff problem. However, it was shown that this only holds if the success rate sss that governs self-adjustment is small enough. Otherwise, even on OneMax, the self-adjusting (1,λ\lambdaλ) EA stagnates on an easy slope, where frequent successes drive down the offspring population size. We show that self-adjustment works as intended in the absence of easy slopes. We define everywhere hard functions, for which successes are never easy to find and show that the self-adjusting (1,λ\lambdaλ) EA is robust with respect to the choice of success rates sss. We give a general fitness-level upper bound on the number of evaluations and show that the expected number of generations is at most O(d+log⁡(1/pmin⁡))O(d + \log(1/p_{\min}))O(d+log(1/pmin​)) where ddd is the number of non-optimal fitness values and pmin⁡p_{\min}pmin​ is the smallest probability of finding an improvement from a non-optimal search point. We discuss implications for the everywhere hard function LeadingOnes and a new class OneMaxBlocks of everywhere hard functions with tunable difficulty.

View on arXiv
Comments on this paper