Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chatalic, Antoine, Schreuder, Nicolas, De Vito, Ernesto, Rosasco, Lorenzo
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913894041124864
author Chatalic, Antoine
Schreuder, Nicolas
De Vito, Ernesto
Rosasco, Lorenzo
author_facet Chatalic, Antoine
Schreuder, Nicolas
De Vito, Ernesto
Rosasco, Lorenzo
contents In this work we consider the problem of numerical integration, i.e., approximating integrals with respect to a target probability measure using only pointwise evaluations of the integrand. We focus on the setting in which the target distribution is only accessible through a set of $n$ i.i.d. observations, and the integrand belongs to a reproducing kernel Hilbert space. We propose an efficient procedure which exploits a small i.i.d. random subset of $m<n$ samples drawn either uniformly or using approximate leverage scores from the initial observations. Our main result is an upper bound on the approximation error of this procedure for both sampling strategies. It yields sufficient conditions on the subsample size to recover the standard (optimal) $n^{-1/2}$ rate while reducing drastically the number of functions evaluations, and thus the overall computational cost. Moreover, we obtain rates with respect to the number $m$ of evaluations of the integrand which adapt to its smoothness, and match known optimal rates for instance for Sobolev spaces. We illustrate our theoretical findings with numerical experiments on real datasets, which highlight the attractive efficiency-accuracy tradeoff of our method compared to existing randomized and greedy quadrature methods. We note that, the problem of numerical integration in RKHS amounts to designing a discrete approximation of the kernel mean embedding of the target distribution. As a consequence, direct applications of our results also include the efficient computation of maximum mean discrepancies between distributions and the design of efficient kernel-based tests.
format Preprint
id arxiv_https___arxiv_org_abs_2311_13548
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling
Chatalic, Antoine
Schreuder, Nicolas
De Vito, Ernesto
Rosasco, Lorenzo
Machine Learning
Numerical Analysis
In this work we consider the problem of numerical integration, i.e., approximating integrals with respect to a target probability measure using only pointwise evaluations of the integrand. We focus on the setting in which the target distribution is only accessible through a set of $n$ i.i.d. observations, and the integrand belongs to a reproducing kernel Hilbert space. We propose an efficient procedure which exploits a small i.i.d. random subset of $m<n$ samples drawn either uniformly or using approximate leverage scores from the initial observations. Our main result is an upper bound on the approximation error of this procedure for both sampling strategies. It yields sufficient conditions on the subsample size to recover the standard (optimal) $n^{-1/2}$ rate while reducing drastically the number of functions evaluations, and thus the overall computational cost. Moreover, we obtain rates with respect to the number $m$ of evaluations of the integrand which adapt to its smoothness, and match known optimal rates for instance for Sobolev spaces. We illustrate our theoretical findings with numerical experiments on real datasets, which highlight the attractive efficiency-accuracy tradeoff of our method compared to existing randomized and greedy quadrature methods. We note that, the problem of numerical integration in RKHS amounts to designing a discrete approximation of the kernel mean embedding of the target distribution. As a consequence, direct applications of our results also include the efficient computation of maximum mean discrepancies between distributions and the design of efficient kernel-based tests.
title Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2311.13548