Geometric Rates of Convergence for Kernel-based Sampling Algorithms
Machine Learning
2021-11-02 v4 Machine Learning
Abstract
The rate of convergence of weighted kernel herding (WKH) and sequential Bayesian quadrature (SBQ), two kernel-based sampling algorithms for estimating integrals with respect to some target probability measure, is investigated. Under verifiable conditions on the chosen kernel and target measure, we establish a near-geometric rate of convergence for target measures that are nearly atomic. Furthermore, we show these algorithms perform comparably to the theoretical best possible sampling algorithm under the maximum mean discrepancy. An analysis is also conducted in a distributed setting. Our theoretical developments are supported by empirical observations on simulated data as well as a real world application.
Cite
@article{arxiv.1907.08410,
title = {Geometric Rates of Convergence for Kernel-based Sampling Algorithms},
author = {Rajiv Khanna and Liam Hodgkinson and Michael W. Mahoney},
journal= {arXiv preprint arXiv:1907.08410},
year = {2021}
}
Comments
Accepted to UAI 2021 (Oral)