arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.06808math.OCstat.ML
收藏

TREGO:一个有效的全球Optimization的置信域框架

TREGO: a Trust-Region Framework for Efficient Global Optimization

Youssef Diouane, Victor Picheny, Rodolphe Le Riche, Alexandre Scotto Di Perrotolo

摘要:

高效全局优化(Efficient Global Optimization,EGO)是贝叶斯优化的标准形式,已成功应用于解决评估费用黑盒问题的全局优化。然而,EGO难以随维度扩展,并且提供了有限的理论保证。在这项工作中,一个置信域框架的EGO(TREGO)的建议和分析。TREGO在置信域内在常规EGO步骤和局部步骤之间交替。通过遵循置信域的经典方案(基于充分减少条件),所提出的算法具有整体收敛特性,而仅在优化步骤的子集上偏离EGO。利用广泛的数值实验的基础上著名的COCO {界约束问题},我们首先分析了TREGO对自己的参数的敏感性,然后表明,由此产生的算法是一贯优于EGO和获得竞争力与其他国家的最先进的黑盒最优化方法。

英文摘要:

Efficient Global Optimization (EGO) is the canonical form of Bayesian optimization that has been successfully applied to solve global optimization of expensive-to-evaluate black-box problems. However, EGO struggles to scale with dimension, and offers limited theoretical guarantees. In this work, a trust-region framework for EGO (TREGO) is proposed and analyzed. TREGO alternates between regular EGO steps and local steps within a trust region. By following a classical scheme for the trust region (based on a sufficient decrease condition), the proposed algorithm enjoys global convergence properties, while departing from EGO only for a subset of optimization steps. Using extensive numerical experiments based on the well-known COCO {bound constrained problems}, we first analyze the sensitivity of TREGO to its own parameters, then show that the resulting algorithm is consistently outperforming EGO and getting competitive with other state-of-the-art black-box optimization methods.

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。

↑