论文标题
NAS-Bench-1Shot1：基准测试和解剖一声神经架构搜索
NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search
论文作者
论文摘要
单发神经体系结构搜索（NAS）在实践中可行的NAS方法中发挥了至关重要的作用。然而，由于控制过程动态的许多因素，仍然缺乏对这些体重共享算法如何正常工作的理解。为了允许对这些组件进行科学研究，我们引入了一个通用框架，用于单发NAS，可以对许多最近引入的变体进行实例化，并引入了一个通用的基准测试框架，该框架借鉴了最近的大型表格基准NAS Benchmark-Bench-Bench-bench-101，以廉价评估一项NAS方法的任何时间。为了展示该框架，我们比较了几种最先进的NAS方法，请检查它们对超参数的敏感性以及如何通过调整其超参数来改进它们，并将其性能与NAS Bench-Bench-bench-bench-101的BlackBox优化器的性能进行比较。
One-shot neural architecture search (NAS) has played a crucial role in making NAS methods computationally feasible in practice. Nevertheless, there is still a lack of understanding on how these weight-sharing algorithms exactly work due to the many factors controlling the dynamics of the process. In order to allow a scientific study of these components, we introduce a general framework for one-shot NAS that can be instantiated to many recently-introduced variants and introduce a general benchmarking framework that draws on the recent large-scale tabular benchmark NAS-Bench-101 for cheap anytime evaluations of one-shot NAS methods. To showcase the framework, we compare several state-of-the-art one-shot NAS methods, examine how sensitive they are to their hyperparameters and how they can be improved by tuning their hyperparameters, and compare their performance to that of blackbox optimizers for NAS-Bench-101.
