Neural architecture search (NAS) has achieved remarkable results in deep neural network design. Differentiable architecture search converts the search over discrete architectures into a hyperparameter optimization problem which can be solved by gradient descent. However, questions have been raised regarding the effectiveness and generalizability of gradient methods for solving non-convex architecture hyperparameter optimization problems. In this paper, we propose L$^{2}$NAS, which learns to intelligently optimize and update architecture hyperparameters via an actor neural network based on the distribution of high-performing architectures in the search history. We introduce a quantile-driven training procedure which efficiently trains L$^{2}$NAS in an actor-critic framework via continuous-action reinforcement learning. Experiments show that L$^{2}$NAS achieves state-of-the-art results on NAS-Bench-201 benchmark as well as DARTS search space and Once-for-All MobileNetV3 search space. We also show that search policies generated by L$^{2}$NAS are generalizable and transferable across different training datasets with minimal fine-tuning.
翻译:在深神经网络设计方面,神经结构搜索(NAS)取得了显著成果。不同的建筑搜索将离散建筑的搜索转换成一个超参数优化问题,可通过梯度下降解决。然而,对于解决非康维克斯建筑超光度优化问题的梯度方法的有效性和通用性提出了问题。在本文中,我们提议用L$2}NAS来学习如何通过一个基于搜索史上高性能建筑分布的演员神经网络来智能优化和更新结构超光谱。我们引入了一个由量化驱动的培训程序,通过持续行动强化学习,将L$2}NAS有效培训在一个演员-critic 框架中。实验显示,L$2}NAS在NAS-Bench-201基准上取得了最新的结果,以及DARTS搜索空间和On-Oll-MobalNetV3搜索空间。我们还表明,L$2}NAS产生的搜索政策是通用的,可以通过微调在不同培训数据集中进行可转让。