Probability error bounds for approximation of functions in reproducing kernel Hilbert spaces

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Aydin, Ata Deniz, Gheondea, Aurelian
Natura: Preprint
Pubblicazione: 2020
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911782189137920
author Aydin, Ata Deniz
Gheondea, Aurelian
author_facet Aydin, Ata Deniz
Gheondea, Aurelian
contents We find probability error bounds for approximations of functions $f$ in a separable reproducing kernel Hilbert space $\mathcal{H}$ with reproducing kernel $K$ on a base space $X$, firstly in terms of finite linear combinations of functions of type $K_{x_i}$ and then in terms of the projection $π^n_x$ on $\mathrm{Span}\{K_{x_i}\}^n_{i=1}$, for random sequences of points $x=(x_i)_i$ in $X$. Given a probability measure $P$, letting $P_K$ be the measure defined by $\mathrm{d} P_K(x)=K(x,x)\mathrm{d} P(x)$, $x\in X$, our approach is based on the nonexpansive operator \[L^2(X;P_K)\niλ\mapsto L_{P,K}λ:=\int_X λ(x)K_x\mathrm{d} P(x)\in \mathcal{H},\] where the integral exists in the Bochner sense. Using this operator, we then define a new reproducing kernel Hilbert space, denoted by $\mathcal{H}_P$, that is the operator range of $L_{P,K}$. Our main result establishes bounds, in terms of the operator $L_{P,K}$, on the probability that the Hilbert space distance between an arbitrary function $f\in\mathcal{H}$ and linear combinations of functions of type $K_{x_i}$, for $(x_i)_i$ sampled independently from $P$, falls below a given threshold. For sequences of points $(x_i)_{i=1}^\infty$ constituting a so-called uniqueness set, the orthogonal projections $π^n_x$ to $\mathrm{Span}\{K_{x_i}\}^n_{i=1}$ converge in the strong operator topology to the identity operator. We prove that, under the assumption that $\mathcal{H}_P$ is dense in $\mathcal{H}$, any sequence of iid samples from $P$ yields a uniqueness set with probability $1$. This result improves on previous error bounds in weaker norms, such as uniform or $L^p$ norms, which yield only convergence in probability and not a.c. convergence. Two examples that show the applicability of this result to a uniform distribution on a compact interval and to the Hardy space $H^2(\mathbb{D})$ are presented as well.
format Preprint
id arxiv_https___arxiv_org_abs_2003_12801
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Probability error bounds for approximation of functions in reproducing kernel Hilbert spaces
Aydin, Ata Deniz
Gheondea, Aurelian
Numerical Analysis
Information Theory
Functional Analysis
Primary 41A65, Secondary 68T05, 46E22
We find probability error bounds for approximations of functions $f$ in a separable reproducing kernel Hilbert space $\mathcal{H}$ with reproducing kernel $K$ on a base space $X$, firstly in terms of finite linear combinations of functions of type $K_{x_i}$ and then in terms of the projection $π^n_x$ on $\mathrm{Span}\{K_{x_i}\}^n_{i=1}$, for random sequences of points $x=(x_i)_i$ in $X$. Given a probability measure $P$, letting $P_K$ be the measure defined by $\mathrm{d} P_K(x)=K(x,x)\mathrm{d} P(x)$, $x\in X$, our approach is based on the nonexpansive operator \[L^2(X;P_K)\niλ\mapsto L_{P,K}λ:=\int_X λ(x)K_x\mathrm{d} P(x)\in \mathcal{H},\] where the integral exists in the Bochner sense. Using this operator, we then define a new reproducing kernel Hilbert space, denoted by $\mathcal{H}_P$, that is the operator range of $L_{P,K}$. Our main result establishes bounds, in terms of the operator $L_{P,K}$, on the probability that the Hilbert space distance between an arbitrary function $f\in\mathcal{H}$ and linear combinations of functions of type $K_{x_i}$, for $(x_i)_i$ sampled independently from $P$, falls below a given threshold. For sequences of points $(x_i)_{i=1}^\infty$ constituting a so-called uniqueness set, the orthogonal projections $π^n_x$ to $\mathrm{Span}\{K_{x_i}\}^n_{i=1}$ converge in the strong operator topology to the identity operator. We prove that, under the assumption that $\mathcal{H}_P$ is dense in $\mathcal{H}$, any sequence of iid samples from $P$ yields a uniqueness set with probability $1$. This result improves on previous error bounds in weaker norms, such as uniform or $L^p$ norms, which yield only convergence in probability and not a.c. convergence. Two examples that show the applicability of this result to a uniform distribution on a compact interval and to the Hardy space $H^2(\mathbb{D})$ are presented as well.
title Probability error bounds for approximation of functions in reproducing kernel Hilbert spaces
topic Numerical Analysis
Information Theory
Functional Analysis
Primary 41A65, Secondary 68T05, 46E22
url https://arxiv.org/abs/2003.12801