Theory of Parameter Control for Discrete Black-Box Optimization: Provable Performance Gains Through Dynamic Parameter Choices

Abstract

Parameter control aims at realizing performance gains through a dynamic choice of the parameters which determine the behavior of the underlying optimization algorithm. In the context of evolutionary algorithms this research line has for a long time been dominated by empirical approaches. With the significant advances in running time analysis achieved in the last ten years, the parameter control question has become accessible to theoretical investigations. A number of running time results for a broad range of different parameter control mechanisms have been obtained in recent years. This book chapter surveys these works, and puts them into context, by proposing an updated classification scheme for parameter control.

References in corpus (3)

• Runtime Analysis of the $(1+(\lambda ,\lambda ))$ Genetic Algorithm on Random Satisfiable 3-CNF Formulas
• The (1+$\lambda$) Evolutionary Algorithm with Self-Adjusting Mutation Rate
• Optimal Parameter Choices Through Self-Adjustment: Applying the 1/5-th Rule in Discrete Settings

Cited by in corpus (15)

• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• Self-Adjusting Evolutionary Algorithms for Multimodal Optimization
• Theoretical Analyses of Multiobjective Evolutionary Algorithms on Multimodal Objectives
• Stagnation Detection with Randomized Local Search
• A Rigorous Runtime Analysis of the $(1+(\lambda ,\lambda ))$ GA on Jump Functions
• Precise Runtime Analysis for Plateau Functions
• How the Move Acceptance Hyper-Heuristic Copes With Local Optima: Drastic Differences Between Jumps and Cliffs
• From Understanding Genetic Drift to a Smart-Restart Mechanism for Estimation-of-Distribution Algorithms
• Towards White-box Benchmarks for Algorithm Control
• Evolutionary Algorithms with Self-adjusting Asymmetric Mutation
• Simple Hyper-heuristics Control the Neighbourhood Size of Randomised Local Search Optimally for LeadingOnes
• An information-theoretic evolutionary algorithm
• Runtime Analysis for Self-adaptive Mutation Rates
• Enhancing Parameter Control Policies with State Information
• Multi-parameter Control for the $(1+(\lambda ,\lambda ))$-GA on OneMax via Deep Reinforcement Learning