Convergence Guarantees for Adaptive Bayesian Quadrature Methods

被引:0
|
作者
Kanagawa, Motonobu [1 ,2 ,3 ]
Hennig, Philipp [2 ,3 ]
机构
[1] EURECOM, Sophia Antipolis, France
[2] Univ Tubingen, Tubingen, Germany
[3] Max Planck Inst Intelligent Syst, Tubingen, Germany
基金
欧洲研究理事会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Adaptive Bayesian quadrature (ABQ) is a powerful approach to numerical integration that empirically compares favorably with Monte Carlo integration on problems of medium dimensionality (where non-adaptive quadrature is not competitive). Its key ingredient is an acquisition function that changes as a function of previously collected values of the integrand. While this adaptivity appears to be empirically powerful, it complicates analysis. Consequently, there are no theoretical guarantees so far for this class of methods. In this work, for a broad class of adaptive Bayesian quadrature methods, we prove consistency, deriving non-tight but informative convergence rates. To do so we introduce a new concept we call weak adaptivity. Our results identify a large and flexible class of adaptive Bayesian quadrature rules as consistent, within which practitioners can develop empirically efficient methods.
引用
收藏
页数:12
相关论文
共 50 条