Neural Architecture Search (NAS) aims to automatically excavate the optimal network architecture with superior test performance. Recent neural architecture search (NAS) approaches rely on validation loss or accuracy to find the superior network for the target data. In this paper, we investigate a new neural architecture search measure for excavating architectures with better generalization. We demonstrate that the flatness of the loss surface can be a promising proxy for predicting the generalization capability of neural network architectures. We evaluate our proposed method on various search spaces, showing similar or even better performance compared to the state-of-the-art NAS methods. Notably, the resultant architecture found by flatness measure generalizes robustly to various shifts in data distribution (e.g. ImageNet-V2,-A,-O), as well as various tasks such as object detection and semantic segmentation. Code is available at https://github.com/clovaai/GeNAS.

翻译：神经架构搜索（NAS）旨在自动挖掘具有优异测试性能的最优网络架构。当前的神经架构搜索方法通常依赖验证损失或准确率来寻找针对目标数据的最优网络。本文研究了一种新的神经架构搜索度量指标，用于挖掘具有更好泛化性能的架构。我们证明损失曲面的平坦度可作为预测神经网络架构泛化能力的有前途的代理指标。我们在多种搜索空间上评估了所提方法，展现出与最先进的NAS方法相当甚至更优的性能。值得注意的是，通过平坦度度量找到的最终架构能够稳健地泛化至数据分布的各种偏移（例如ImageNet-V2、-A、-O）以及目标检测、语义分割等多种任务。代码开源在https://github.com/clovaai/GeNAS。