Evolution-based neural architecture search requires high computational resources, resulting in long search time. In this work, we propose a framework of applying the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to the neural architecture search problem called CMANAS, which achieves better results than previous evolution-based methods while reducing the search time significantly. The architectures are modelled using a normal distribution, which is updated using CMA-ES based on the fitness of the sampled population. We used the accuracy of a trained one shot model (OSM) on the validation data as a prediction of the fitness of an individual architecture to reduce the search time. We also used an architecture-fitness table (AF table) for keeping record of the already evaluated architecture, thus further reducing the search time. CMANAS finished the architecture search on CIFAR-10 with the top-1 test accuracy of 97.44% in 0.45 GPU day and on CIFAR-100 with the top-1 test accuracy of 83.24% for 0.6 GPU day on a single GPU. The top architectures from the searches on CIFAR-10 and CIFAR-100 were then transferred to ImageNet, achieving the top-5 accuracy of 92.6% and 92.1%, respectively.

中文翻译：

---

使用协方差矩阵自适应进化策略的神经架构搜索

基于进化的神经架构搜索需要大量的计算资源，导致搜索时间长。在这项工作中，我们提出了一个将协方差矩阵适应进化策略 (CMA-ES) 应用于称为 CMANAS 的神经架构搜索问题的框架，该框架比以前的基于进化的方法取得了更好的结果，同时显着减少了搜索时间。体系结构使用正态分布建模，正态分布使用 CMA-ES 根据采样总体的适应度进行更新。我们在验证数据上使用经过训练的一次性模型 (OSM) 的准确性作为对单个架构的适应度的预测，以减少搜索时间。我们还使用了架构适应表（AF 表）来记录已经评估过的架构，从而进一步减少了搜索时间。CMANAS在CIFAR-10上以0.45个GPU日的top-1测试准确率为97.44%完成了架构搜索，在CIFAR-100上在单个GPU上以0.6个GPU日的top-1测试准确率为83.24%。然后将 CIFAR-10 和 CIFAR-100 搜索的顶级架构转移到 ImageNet，分别实现了 92.6% 和 92.1% 的 top-5 准确率。