Neural Architecture Search (NAS) has demonstrated state-of-the-art performance on various computer vision tasks. Despite the superior performance achieved, the efficiency and generality of existing methods are highly valued due to their high computational complexity and low generality. In this paper, we propose an efficient and unified NAS framework termed DDPNAS via dynamic distribution pruning, facilitating a theoretical bound on accuracy and efficiency. In particular, we first sample architectures from a joint categorical distribution. Then the search space is dynamically pruned and its distribution is updated every few epochs. With the proposed efficient network generation method, we directly obtain the optimal neural architectures on given constraints, which is practical for on-device models across diverse search spaces and constraints. The architectures searched by our method achieve remarkable top-1 accuracies, 97.56 and 77.2 on CIFAR-10 and ImageNet (mobile settings), respectively, with the fastest search process, i.e., only 1.8 GPU hours on a Tesla V100. Codes for searching and network generation are available at: https://openi.pcl.ac.cn/PCL AutoML/XNAS.

翻译：神经架构搜索（NAS）已在多项计算机视觉任务中展现出最先进的性能。尽管取得了优异表现，但现有方法因计算复杂度高、泛化能力低，其效率与通用性备受关注。本文提出一种名为DDPNAS的高效统一NAS框架，通过动态分布剪枝实现精度与效率的理论边界优化。具体而言，我们首先从联合类别分布中采样架构，随后每若干训练周期动态剪枝搜索空间并更新其分布。借助所提出的高效网络生成方法，我们可直接在给定约束条件下获得最优神经架构，该方法对跨多样搜索空间与约束条件的端侧模型具有实用价值。本方法搜索得到的架构在CIFAR-10和ImageNet（移动端设置）上分别取得97.56%和77.2%的出色Top-1准确率，且搜索过程极快——在Tesla V100上仅需1.8 GPU小时。搜索与网络生成代码已开源：https://openi.pcl.ac.cn/PCL AutoML/XNAS。