Distributed Evolution Strategies with Multi-Level Learning for Large-Scale Black-Box Optimization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Duan, Qiqi, Shao, Chang, Zhou, Guochen, Zhang, Minghan, Zhao, Qi, Shi, Yuhui
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916432683466752
author Duan, Qiqi
Shao, Chang
Zhou, Guochen
Zhang, Minghan
Zhao, Qi
Shi, Yuhui
author_facet Duan, Qiqi
Shao, Chang
Zhou, Guochen
Zhang, Minghan
Zhao, Qi
Shi, Yuhui
contents In the post-Moore era, main performance gains of black-box optimizers are increasingly depending on parallelism, especially for large-scale optimization (LSO). Here we propose to parallelize the well-established covariance matrix adaptation evolution strategy (CMA-ES) and in particular its one latest LSO variant called limited-memory CMA-ES (LM-CMA). To achieve efficiency while approximating its powerful invariance property, we present a multilevel learning-based meta-framework for distributed LM-CMA. Owing to its hierarchically organized structure, Meta-ES is well-suited to implement our distributed meta-framework, wherein the outer-ES controls strategy parameters while all parallel inner-ESs run the serial LM-CMA with different settings. For the distribution mean update of the outer-ES, both the elitist and multi-recombination strategy are used in parallel to avoid stagnation and regression, respectively. To exploit spatiotemporal information, the global step-size adaptation combines Meta-ES with the parallel cumulative step-size adaptation. After each isolation time, our meta-framework employs both the structure and parameter learning strategy to combine aligned evolution paths for CMA reconstruction. Experiments on a set of large-scale benchmarking functions with memory-intensive evaluations, arguably reflecting many data-driven optimization problems, validate the benefits (e.g., effectiveness w.r.t. solution quality, and adaptability w.r.t. second-order learning) and costs of our meta-framework.
format Preprint
id arxiv_https___arxiv_org_abs_2310_05377
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Distributed Evolution Strategies with Multi-Level Learning for Large-Scale Black-Box Optimization
Duan, Qiqi
Shao, Chang
Zhou, Guochen
Zhang, Minghan
Zhao, Qi
Shi, Yuhui
Neural and Evolutionary Computing
In the post-Moore era, main performance gains of black-box optimizers are increasingly depending on parallelism, especially for large-scale optimization (LSO). Here we propose to parallelize the well-established covariance matrix adaptation evolution strategy (CMA-ES) and in particular its one latest LSO variant called limited-memory CMA-ES (LM-CMA). To achieve efficiency while approximating its powerful invariance property, we present a multilevel learning-based meta-framework for distributed LM-CMA. Owing to its hierarchically organized structure, Meta-ES is well-suited to implement our distributed meta-framework, wherein the outer-ES controls strategy parameters while all parallel inner-ESs run the serial LM-CMA with different settings. For the distribution mean update of the outer-ES, both the elitist and multi-recombination strategy are used in parallel to avoid stagnation and regression, respectively. To exploit spatiotemporal information, the global step-size adaptation combines Meta-ES with the parallel cumulative step-size adaptation. After each isolation time, our meta-framework employs both the structure and parameter learning strategy to combine aligned evolution paths for CMA reconstruction. Experiments on a set of large-scale benchmarking functions with memory-intensive evaluations, arguably reflecting many data-driven optimization problems, validate the benefits (e.g., effectiveness w.r.t. solution quality, and adaptability w.r.t. second-order learning) and costs of our meta-framework.
title Distributed Evolution Strategies with Multi-Level Learning for Large-Scale Black-Box Optimization
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2310.05377