Neural architecture search (NAS) has gained immense popularity owing to its ability to automate neural architecture design. A number of training-free metrics are recently proposed to realize NAS without training, hence making NAS more scalable. Despite their competitive empirical performances, a unified theoretical understanding of these training-free metrics is lacking. As a consequence, (a) the relationships among these metrics are unclear, (b) there is no theoretical guarantee for their empirical performances and transferability, and (c) there may exist untapped potential in training-free NAS, which can be unveiled through a unified theoretical understanding. To this end, this paper presents a unified theoretical analysis of gradient-based training-free NAS, which allows us to (a) theoretically study their relationships, (b) theoretically guarantee their generalization performances and transferability, and (c) exploit our unified theoretical understanding to develop a novel framework named hybrid NAS (HNAS) which consistently boosts training-free NAS in a principled way. Interestingly, HNAS is able to enjoy the advantages of both training-free (i.e., superior search efficiency) and training-based (i.e., remarkable search effectiveness) NAS, which we have demonstrated through extensive experiments.

本文提出了一个统一的理论分析框架来研究基于梯度的免训练神经构架搜索方法，从而理论上研究它们之间的关系、保证它们的泛化性能并开发一种名为Hybrid NAS(HNAS)的新框架，它在原则上可以持续提高训练免费NAS的效果。

基于渐变的训练免费神经结构搜索的统一和增强