用强化学习搜索神经网络架构，能高效探索大空间但对超参敏感。
Scalable Reinforcement Learning-based Neural Architecture Search
- 强化学习代理自主搜索架构，不依赖单一最优解。
- 在NAS-Bench-101/301上表现优于随机与局部搜索基线。
- 搜索空间越大越有优势，但超参数调整影响结果稳定性。
本文评估了一种基于强化学习的新型神经架构搜索方法，其中强化学习代理学习自主搜索优质架构，而非仅返回单一最优架构。在NAS-Bench-101和NAS-Bench-301设置下，与多种强基线（如局部搜索、随机搜索）对比，结果显示该代理在搜索空间规模扩大时表现出显著可扩展性，但在超参数变化下鲁棒性较弱。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。