Wasserstein Evolution : Evolutionary Optimization as Phase Transition

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ouyang, Kaichen, Yu, Mingyang, Ke, Zong, Lian, Junbo Jacob, Fu, Shengwei, Hao, Xiaoyang, Yu, Shengju, Hu, Dayu
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912831357583360
author Ouyang, Kaichen
Yu, Mingyang
Ke, Zong
Lian, Junbo Jacob
Fu, Shengwei
Hao, Xiaoyang
Yu, Shengju
Hu, Dayu
author_facet Ouyang, Kaichen
Yu, Mingyang
Ke, Zong
Lian, Junbo Jacob
Fu, Shengwei
Hao, Xiaoyang
Yu, Shengju
Hu, Dayu
contents Evolutionary algorithms (EAs) serve as powerful black-box optimizers inspired by biological evolution. However, most existing EAs predominantly focus on heuristic operators such as crossover and mutation, while usually overlooking underlying physical interpretability such as statistical mechanics and thermosdynamics. This theoretical void limits the principled understanding of algorithmic dynamics, hindering the systematic design of evolutionary search beyond ad-hoc heuristics. To bridge this gap, we first point out that evolutionary optimization can be conceptually reframed as a physical phase transition process. Building on this perspective, we establish the theoretical grounds by modeling the optimization dynamics as a Wasserstein gradient flow of free energy. Consequently, a robust and interpretable solver named Wasserstein Evolution (WE) is proposed. WE mathematically frames the trade-off between exploration and exploitation as a competition between potential gradient forces and entropic forces. This formulation guarantees convergence to the Boltzmann distribution, thereby minimizing free energy and maximizing entropy, which promotes highly diverse solutions. Extensive experiments on complex multimodal and physical potential functions demonstrate that WE achieves superior diversity and stability compared to established baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05837
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Wasserstein Evolution : Evolutionary Optimization as Phase Transition
Ouyang, Kaichen
Yu, Mingyang
Ke, Zong
Lian, Junbo Jacob
Fu, Shengwei
Hao, Xiaoyang
Yu, Shengju
Hu, Dayu
Neural and Evolutionary Computing
Evolutionary algorithms (EAs) serve as powerful black-box optimizers inspired by biological evolution. However, most existing EAs predominantly focus on heuristic operators such as crossover and mutation, while usually overlooking underlying physical interpretability such as statistical mechanics and thermosdynamics. This theoretical void limits the principled understanding of algorithmic dynamics, hindering the systematic design of evolutionary search beyond ad-hoc heuristics. To bridge this gap, we first point out that evolutionary optimization can be conceptually reframed as a physical phase transition process. Building on this perspective, we establish the theoretical grounds by modeling the optimization dynamics as a Wasserstein gradient flow of free energy. Consequently, a robust and interpretable solver named Wasserstein Evolution (WE) is proposed. WE mathematically frames the trade-off between exploration and exploitation as a competition between potential gradient forces and entropic forces. This formulation guarantees convergence to the Boltzmann distribution, thereby minimizing free energy and maximizing entropy, which promotes highly diverse solutions. Extensive experiments on complex multimodal and physical potential functions demonstrate that WE achieves superior diversity and stability compared to established baselines.
title Wasserstein Evolution : Evolutionary Optimization as Phase Transition
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2512.05837