arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.03586cs.LGmath.OCstat.ML
收藏

基于序贯均匀设计的超参数优化

Hyperparameter Optimization via Sequential Uniform Designs

University of Hong Kong(香港大学)

Zebin Yang, Aijun Zhang

摘要:

超参数优化(HPO)在自动机器学习(AutoML)中起着核心作用。这是一个具有挑战性的任务,因为超参数的响应曲面通常是未知的,因此本质上是一个全局优化问题。本文将HPO转化为计算机实验,提出了一种新的顺序均匀设计(SeqUD)策略,该策略具有以下三个优点:a)均匀分布的设计点自适应地探索超参数空间,而不需要昂贵的元建模和获取优化; b)在并行处理支持下,逐批顺序生成设计点;(3)提出了一种新的增广均匀设计算法,用于有效地实时生成后续设计点。在全局优化任务和HPO应用程序上进行了大量的实验。数值结果表明,所提出的SeqUD策略优于基准HPO方法,因此它可以成为现有AutoML工具的有前途和有竞争力的替代方案。

英文摘要:

Hyperparameter optimization (HPO) plays a central role in the automated machine learning (AutoML). It is a challenging task as the response surfaces of hyperparameters are generally unknown, hence essentially a global optimization problem. This paper reformulates HPO as a computer experiment and proposes a novel sequential uniform design (SeqUD) strategy with three-fold advantages: a) the hyperparameter space is adaptively explored with evenly spread design points, without the need of expensive meta-modeling and acquisition optimization; b) the batch-by-batch design points are sequentially generated with parallel processing support; c) a new augmented uniform design algorithm is developed for the efficient real-time generation of follow-up design points. Extensive experiments are conducted on both global optimization tasks and HPO applications. The numerical results show that the proposed SeqUD strategy outperforms benchmark HPO methods, and it can be therefore a promising and competitive alternative to existing AutoML tools.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑