GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917728668876800 |
|---|---|
| author | Liang, Zhenyu Jiang, Tao Sun, Kebin Cheng, Ran |
| author_facet | Liang, Zhenyu Jiang, Tao Sun, Kebin Cheng, Ran |
| contents | Evolutionary multiobjective optimization has witnessed remarkable progress during the past decades. However, existing algorithms often encounter computational challenges in large-scale scenarios, primarily attributed to the absence of hardware acceleration. In response, we introduce a Tensorized Reference Vector Guided Evolutionary Algorithm (TensorRVEA) for harnessing the advancements of GPU acceleration. In TensorRVEA, the key data structures and operators are fully transformed into tensor forms for leveraging GPU-based parallel computing. In numerical benchmark tests involving large-scale populations and problem dimensions, TensorRVEA consistently demonstrates high computational performance, achieving up to over 1000$\times$ speedups. Then, we applied TensorRVEA to the domain of multiobjective neuroevolution for addressing complex challenges in robotic control tasks. Furthermore, we assessed TensorRVEA's extensibility by altering several tensorized reproduction operators. Experimental results demonstrate promising scalability and robustness of TensorRVEA. Source codes are available at \url{https://github.com/EMI-Group/tensorrvea}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01159 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA Liang, Zhenyu Jiang, Tao Sun, Kebin Cheng, Ran Neural and Evolutionary Computing Evolutionary multiobjective optimization has witnessed remarkable progress during the past decades. However, existing algorithms often encounter computational challenges in large-scale scenarios, primarily attributed to the absence of hardware acceleration. In response, we introduce a Tensorized Reference Vector Guided Evolutionary Algorithm (TensorRVEA) for harnessing the advancements of GPU acceleration. In TensorRVEA, the key data structures and operators are fully transformed into tensor forms for leveraging GPU-based parallel computing. In numerical benchmark tests involving large-scale populations and problem dimensions, TensorRVEA consistently demonstrates high computational performance, achieving up to over 1000$\times$ speedups. Then, we applied TensorRVEA to the domain of multiobjective neuroevolution for addressing complex challenges in robotic control tasks. Furthermore, we assessed TensorRVEA's extensibility by altering several tensorized reproduction operators. Experimental results demonstrate promising scalability and robustness of TensorRVEA. Source codes are available at \url{https://github.com/EMI-Group/tensorrvea}. |
| title | GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2404.01159 |