Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Jiacheng, Ma, Zeyuan, Guo, Hongshu, Ma, Yining, Zhang, Jie, Gong, Yue-Jiao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916117445869568
author Chen, Jiacheng
Ma, Zeyuan
Guo, Hongshu
Ma, Yining
Zhang, Jie
Gong, Yue-Jiao
author_facet Chen, Jiacheng
Ma, Zeyuan
Guo, Hongshu
Ma, Yining
Zhang, Jie
Gong, Yue-Jiao
contents Recent Meta-learning for Black-Box Optimization (MetaBBO) methods harness neural networks to meta-learn configurations of traditional black-box optimizers. Despite their success, they are inevitably restricted by the limitations of predefined hand-crafted optimizers. In this paper, we present \textsc{Symbol}, a novel framework that promotes the automated discovery of black-box optimizers through symbolic equation learning. Specifically, we propose a Symbolic Equation Generator (SEG) that allows closed-form optimization rules to be dynamically generated for specific tasks and optimization steps. Within \textsc{Symbol}, we then develop three distinct strategies based on reinforcement learning, so as to meta-learn the SEG efficiently. Extensive experiments reveal that the optimizers generated by \textsc{Symbol} not only surpass the state-of-the-art BBO and MetaBBO baselines, but also exhibit exceptional zero-shot generalization abilities across entirely unseen tasks with different problem dimensions, population sizes, and optimization horizons. Furthermore, we conduct in-depth analyses of our \textsc{Symbol} framework and the optimization rules that it generates, underscoring its desirable flexibility and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02355
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
Chen, Jiacheng
Ma, Zeyuan
Guo, Hongshu
Ma, Yining
Zhang, Jie
Gong, Yue-Jiao
Machine Learning
Neural and Evolutionary Computing
Recent Meta-learning for Black-Box Optimization (MetaBBO) methods harness neural networks to meta-learn configurations of traditional black-box optimizers. Despite their success, they are inevitably restricted by the limitations of predefined hand-crafted optimizers. In this paper, we present \textsc{Symbol}, a novel framework that promotes the automated discovery of black-box optimizers through symbolic equation learning. Specifically, we propose a Symbolic Equation Generator (SEG) that allows closed-form optimization rules to be dynamically generated for specific tasks and optimization steps. Within \textsc{Symbol}, we then develop three distinct strategies based on reinforcement learning, so as to meta-learn the SEG efficiently. Extensive experiments reveal that the optimizers generated by \textsc{Symbol} not only surpass the state-of-the-art BBO and MetaBBO baselines, but also exhibit exceptional zero-shot generalization abilities across entirely unseen tasks with different problem dimensions, population sizes, and optimization horizons. Furthermore, we conduct in-depth analyses of our \textsc{Symbol} framework and the optimization rules that it generates, underscoring its desirable flexibility and interpretability.
title Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2402.02355