The field of Automatic Machine Learning (AutoML) has recently attained impressive results, including the discovery of state-of-the-art machine learning solutions, such as neural image classifiers. This is often done by applying an evolutionary search method, which samples multiple candidate solutions from a large space and evaluates the quality of each candidate through a long training process. As a result, the search tends to be slow. In this paper, we show that large efficiency gains can be obtained by employing a fast unified functional hash, especially through the functional equivalence caching technique, which we also present. The central idea is to detect by hashing when the search method produces equivalent candidates, which occurs very frequently, and this way avoid their costly re-evaluation. Our hash is "functional" in that it identifies equivalent candidates even if they were represented or coded differently, and it is "unified" in that the same algorithm can hash arbitrary representations; e.g. compute graphs, imperative code, or lambda functions. As evidence, we show dramatic improvements on multiple AutoML domains, including neural architecture search and algorithm discovery. Finally, we consider the effect of hash collisions, evaluation noise, and search distribution through empirical analysis. Altogether, we hope this paper may serve as a guide to hashing techniques in AutoML.

翻译：自动机器学习(Automal)领域最近取得了令人印象深刻的成果,包括发现了最先进的机器学习解决方案,例如神经图像分类器。这通常通过应用进化搜索方法来实现,该方法从一个大空间对多个候选解决方案进行抽样,并通过一个漫长的培训过程对每个候选人的质量进行评估。结果,搜索过程往往很慢。在本文中,我们显示,通过快速统一的功能散列,特别是我们也存在的功能等同缓缓冲技术,可以取得巨大的效率收益。中心思想是,在搜索方法产生同等候选人时,通过散测,这种方法经常发生,避免费用高昂的重新评价。最后,我们的 " 功能 " 在于,它识别了同等候选人,即使这些候选人有不同的表述或编码,也是不同的。因此,同样的算法可能具有任意的表述方式,例如,编造图表、必备代码或羊角函数。作为证据,我们展示了多个自动移动系统领域的巨大改进,包括神经结构搜索和算法发现。最后,我们认为,我们的“功能 " 功能 " 功能化分析 ",通过这种图像分析,我们可能成为了一种对结果的分析。