English

Convergence Guarantees for Adaptive Bayesian Quadrature Methods

Machine Learning 2019-10-29 v2 Machine Learning Numerical Analysis Numerical Analysis Computation

Abstract

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.

Keywords

Cite

@article{arxiv.1905.10271,
  title  = {Convergence Guarantees for Adaptive Bayesian Quadrature Methods},
  author = {Motonobu Kanagawa and Philipp Hennig},
  journal= {arXiv preprint arXiv:1905.10271},
  year   = {2019}
}

Comments

To appear in NeurIPS 2019

R2 v1 2026-06-23T09:22:31.072Z