تقرير
Massively Parallel Genetic Optimization through Asynchronous Propagation of Populations
| العنوان: | Massively Parallel Genetic Optimization through Asynchronous Propagation of Populations |
|---|---|
| المؤلفون: | Taubert, Oskar, Weiel, Marie, Coquelin, Daniel, Farshian, Anis, Debus, Charlotte, Schug, Alexander, Streit, Achim, Götz, Markus |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Neural and Evolutionary Computing, Computer Science - Distributed, Parallel, and Cluster Computing, 68T05, 68W50, I.2.8 |
| الوصف: | We present Propulate, an evolutionary optimization algorithm and software package for global optimization and in particular hyperparameter search. For efficient use of HPC resources, Propulate omits the synchronization after each generation as done in conventional genetic algorithms. Instead, it steers the search with the complete population present at time of breeding new individuals. We provide an MPI-based implementation of our algorithm, which features variants of selection, mutation, crossover, and migration and is easy to extend with custom functionality. We compare Propulate to the established optimization tool Optuna. We find that Propulate is up to three orders of magnitude faster without sacrificing solution accuracy, demonstrating the efficiency and efficacy of our lazy synchronization approach. Code and documentation are available at https://github.com/Helmholtz-AI-Energy/propulate Comment: 18 pages, 5 figures submitted to ISC High Performance 2023 |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1007/978-3-031-32041-5_6 |
| URL الوصول: | http://arxiv.org/abs/2301.08713 |
| رقم الأكسشن: | edsarx.2301.08713 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1007/978-3-031-32041-5_6 |
|---|