Designing neural architectures requires immense manual efforts. This has
promoted the development of neural architecture search (NAS) to automate the
design. While previous NAS methods achieve promising results but run slowly,
zero-cost proxies run extremely fast but are less promising. Therefore, it is
of great potential to accelerate NAS via those zero-cost proxies. The existing
method has two limitations, which are unforeseeable reliability and one-shot
usage. To address the limitations, we present ProxyBO, an efficient Bayesian
optimization (BO) framework that utilizes the zero-cost proxies to accelerate
neural architecture search. We apply the generalization ability measurement to
estimate the fitness of proxies on the task during each iteration and design a
novel acquisition function to combine BO with zero-cost proxies based on their
dynamic influence. Extensive empirical studies show that ProxyBO consistently
outperforms competitive baselines on five tasks from three public benchmarks.
Concretely, ProxyBO achieves up to 5.41x and 3.86x speedups over the
state-of-the-art approaches REA and BRP-NAS.

本论文提出了 ProxyBO，一种利用零成本代理加速神经架构搜索的高效贝叶斯优化（BO）框架，通过我们设计的新颖获取函数结合动态影响的零成本代理，以及利用一般化能力测量估计代理在每个迭代期间的适应性，ProxyBO 在三个公共基准测试任务中的五个任务上持续超越竞争对手 REA 和 BRP-NAS，达到了 5.41x 和 3.86x 的加速。