arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.09009cs.LGstat.ML
收藏

BORE:密度比估计的贝叶斯优化

BORE: Bayesian Optimization by Density-Ratio Estimation

University of Sydney(悉尼大学);CSIRO’s Data61(联邦科学与工业研究组织Data61);Amazon(亚马逊);NVIDIA(英伟达)

Louis C. Tiao, Aaron Klein, Matthias Seeger, Edwin V. Bonilla, Cedric Archambeau, Fabio Ramos

摘要:

贝叶斯优化(BO)是最有效和最广泛使用的黑盒优化方法之一。BO提出的解决方案,根据探索利用权衡标准编码的采集功能,其中许多是计算从后验预测的概率代理模型。其中普遍存在的是预期改善(EI)功能。确保预测的分析易处理性的需求通常会带来限制,这些限制可能会阻碍BO的效率和适用性。在本文中,我们投EI的计算作为一个二元分类问题,建立在类概率估计和密度比估计之间的联系,以及密度比和EI之间的鲜为人知的联系。通过规避易处理性约束,这种重构提供了许多优点,尤其是在表达性、多功能性和可伸缩性方面。

英文摘要:

Bayesian optimization (BO) is among the most effective and widely-used blackbox optimization methods. BO proposes solutions according to an explore-exploit trade-off criterion encoded in an acquisition function, many of which are computed from the posterior predictive of a probabilistic surrogate model. Prevalent among these is the expected improvement (EI) function. The need to ensure analytical tractability of the predictive often poses limitations that can hinder the efficiency and applicability of BO. In this paper, we cast the computation of EI as a binary classification problem, building on the link between class-probability estimation and density-ratio estimation, and the lesser-known link between density-ratios and EI. By circumventing the tractability constraints, this reformulation provides numerous advantages, not least in terms of expressiveness, versatility, and scalability.

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。

↑