Using Automated Algorithm Configuration for Parameter Control

DOI10.1145/3594805.3607127arXiv2302.12334WikidataQ130906105 ScholiaQ130906105MaRDI QIDQ6202151FDOQ6202151

Authors:

Publication date: 23 February 2024

Published in: Proceedings of the 17th ACM/SIGEVO Conference on Foundations of Genetic Algorithms (Search for Journal in Brave)

Abstract: Dynamic Algorithm Configuration (DAC) tackles the question of how to automatically learn policies to control parameters of algorithms in a data-driven fashion. This question has received considerable attention from the evolutionary community in recent years. Having a good benchmark collection to gain structural understanding on the effectiveness and limitations of different solution methods for DAC is therefore strongly desirable. Following recent work on proposing DAC benchmarks with well-understood theoretical properties and ground truth information, in this work, we suggest as a new DAC benchmark the controlling of the key parameter $lambda$ in the $(1+(lambda,lambda))$~Genetic Algorithm for solving OneMax problems. We conduct a study on how to solve the DAC problem via the use of (static) automated algorithm configuration on the benchmark, and propose techniques to significantly improve the performance of the approach. Our approach is able to consistently outperform the default parameter control policy of the benchmark derived from previous theoretical work on sufficiently large problem sizes. We also present new findings on the landscape of the parameter-control search policies and propose methods to compute stronger baselines for the benchmark via numerical approximations of the true optimal policies.

Full work available at URL: https://arxiv.org/abs/2302.12334

zbMATH Keywords

benchmarkinggenetic algorithmsalgorithm configurationevolutionary computationparameter control

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Approximation methods and heuristics in mathematical programming (90C59) Evolutionary algorithms, genetic algorithms (computational aspects) (68W50)

Cites Work

• Learning probability distributions in continuous evolutionary algorithms -- a comparative review
• Black-box search by unbiased variation
• Playing mastermind with constant-size memory
• Analyzing bandit-based adaptive operator selection mechanisms
• From black-box complexity to designing new genetic algorithms
• An experimental study of operator choices in the \((1+(\lambda,\lambda))\) genetic algorithm
• Analyzing randomized search heuristics via stochastic domination
• Optimal static and self-adjusting parameter choices for the \((1+(\lambda ,\lambda ))\) genetic algorithm
• A deep reinforcement learning based hyper-heuristic for combinatorial optimisation with uncertainties
• A tight runtime analysis for the \((1+(\lambda,\lambda))\) GA on LeadingOnes
• A rigorous runtime analysis of the \((1 + (\lambda, \lambda))\) GA on jump functions
• Fast mutation in crossover-based algorithms
• Capping methods for the automatic configuration of optimization algorithms
• Automated Dynamic Algorithm Configuration

This page was built for publication: Using Automated Algorithm Configuration for Parameter Control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6202151)