Szczegóły publikacji
Opis bibliograficzny
pyHMS: a Python library for Hierarchic Memetic Strategy / Wojciech ACHTELIK, Hubert GUZOWSKI, Maciej SMOŁKA // W: GECCO'25 Companion [Dokument elektroniczny] : proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion : July 14–18, 2025, Málaga, Spain. — Wersja do Windows. — Dane tekstowe. — New York : Association for Computing Machinery, 2025. — e-ISBN: 979-8-4007-1464-1. — S. 2055–2062. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 2061–2062, Abstr. — Publikacja dostępna online od: 2025-08-11
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 161863 |
|---|---|
| Data dodania do BaDAP | 2025-09-03 |
| Tekst źródłowy | URL |
| DOI | 10.1145/3712255.3734342 |
| Rok publikacji | 2025 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Creative Commons | |
| Wydawca | Association for Computing Machinery (ACM) |
| Konferencja | Genetic and Evolutionary Computations 2025 |
Abstract
In this paper, we introduce pyHMS, a comprehensive open-source Python implementation of the Hierarchic Memetic Strategy (HMS) algorithm, designed to address complex multimodal optimization problems. HMS employs a tree-like structure where multiple populations managed by different metaheuristics operate with limited communication, enhancing solution diversity while balancing exploration and exploitation through hierarchical organization. Our implementation consolidates various HMS advancements from the literature and in some cases provides expanded versions of what was presented. The code architecture is modular and easily extendable, supporting both a high-level interface for practitioners and detailed control for researchers, facilitating experimentation with novel configurations and hybridization of different metaheuristics. The library also provides a set of ready-made tools, which include implementations of niching techniques, widely recognized and novel optimization algorithms, visualization capabilities, and landscape approximation methods. The goal of pyHMS library is to provide a toolbox for tackling complex real-world problems and to encourage the use of this framework as a basis for the creation of novel, hybrid optimization algorithms.
