Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.01431 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910751805931520 |
|---|---|
| author | Cassimon, Amber Mercelis, Siegfried Mets, Kevin |
| author_facet | Cassimon, Amber Mercelis, Siegfried Mets, Kevin |
| contents | In this publication, we assess the ability of a novel Reinforcement Learning-based solution to the problem of Neural Architecture Search, where a Reinforcement Learning (RL) agent learns to search for good architectures, rather than to return a single optimal architecture. We consider both the NAS-Bench-101 and NAS- Bench-301 settings, and compare against various known strong baselines, such as local search and random search. We conclude that our Reinforcement Learning agent displays strong scalability with regards to the size of the search space, but limited robustness to hyperparameter changes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01431 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Scalable Reinforcement Learning-based Neural Architecture Search Cassimon, Amber Mercelis, Siegfried Mets, Kevin Machine Learning In this publication, we assess the ability of a novel Reinforcement Learning-based solution to the problem of Neural Architecture Search, where a Reinforcement Learning (RL) agent learns to search for good architectures, rather than to return a single optimal architecture. We consider both the NAS-Bench-101 and NAS- Bench-301 settings, and compare against various known strong baselines, such as local search and random search. We conclude that our Reinforcement Learning agent displays strong scalability with regards to the size of the search space, but limited robustness to hyperparameter changes. |
| title | Scalable Reinforcement Learning-based Neural Architecture Search |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.01431 |