Neural Genetic Search in Discrete Spaces
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911007647989760 |
|---|---|
| author | Kim, Hyeonah Choi, Sanghyeok Son, Jiwoo Park, Jinkyoo Kwon, Changhyun |
| author_facet | Kim, Hyeonah Choi, Sanghyeok Son, Jiwoo Park, Jinkyoo Kwon, Changhyun |
| contents | Effective search methods are crucial for improving the performance of deep generative models at test time. In this paper, we introduce a novel test-time search method, Neural Genetic Search (NGS), which incorporates the evolutionary mechanism of genetic algorithms into the generation procedure of deep models. The core idea behind NGS is its crossover, which is defined as parent-conditioned generation using trained generative models. This approach offers a versatile and easy-to-implement search algorithm for deep generative models. We demonstrate the effectiveness and flexibility of NGS through experiments across three distinct domains: routing problems, adversarial prompt generation for language models, and molecular design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10433 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Genetic Search in Discrete Spaces Kim, Hyeonah Choi, Sanghyeok Son, Jiwoo Park, Jinkyoo Kwon, Changhyun Neural and Evolutionary Computing Machine Learning Effective search methods are crucial for improving the performance of deep generative models at test time. In this paper, we introduce a novel test-time search method, Neural Genetic Search (NGS), which incorporates the evolutionary mechanism of genetic algorithms into the generation procedure of deep models. The core idea behind NGS is its crossover, which is defined as parent-conditioned generation using trained generative models. This approach offers a versatile and easy-to-implement search algorithm for deep generative models. We demonstrate the effectiveness and flexibility of NGS through experiments across three distinct domains: routing problems, adversarial prompt generation for language models, and molecular design. |
| title | Neural Genetic Search in Discrete Spaces |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2502.10433 |