Random sections of ellipsoids and the power of random information

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hinrichs, Aicke, Krieg, David, Novak, Erich, Prochno, Joscha, Ullrich, Mario
Format: Preprint
Published: 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929538804482048
author Hinrichs, Aicke
Krieg, David
Novak, Erich
Prochno, Joscha
Ullrich, Mario
author_facet Hinrichs, Aicke
Krieg, David
Novak, Erich
Prochno, Joscha
Ullrich, Mario
contents We study the circumradius of the intersection of an $m$-dimensional ellipsoid $\mathcal E$ with semi-axes $σ_1\geq\dots\geq σ_m$ with random subspaces of codimension $n$. We find that, under certain assumptions on $σ$, this random radius $\mathcal{R}_n=\mathcal{R}_n(σ)$ is of the same order as the minimal such radius $σ_{n+1}$ with high probability. In other situations $\mathcal{R}_n$ is close to the maximum $σ_1$. The random variable $\mathcal{R}_n$ naturally corresponds to the worst-case error of the best algorithm based on random information for $L_2$-approximation of functions from a compactly embedded Hilbert space $H$ with unit ball $\mathcal E$. In particular, $σ_k$ is the $k$th largest singular value of the embedding $H\hookrightarrow L_2$. In this formulation, one can also consider the case $m=\infty$, and we prove that random information behaves very differently depending on whether $σ\in \ell_2$ or not. For $σ\notin \ell_2$ random information is completely useless, i.e., $\mathbb E[\mathcal{R}_n] = σ_1$. For $σ\in \ell_2$ the expected radius of random information tends to zero at least at rate $o(1/\sqrt{n})$ as $n\to\infty$. In the important case $σ_k \asymp k^{-α} \ln^{-β}(k+1)$, where $α> 0$ and $β\in\mathbb R$, we obtain that $$ \mathbb E [\mathcal{R}_n(σ)] \asymp \begin{cases} σ_1 & : α<1/2 \,\text{ or }\, β\leqα=1/2 \\ σ_n \, \sqrt{\ln(n+1)} & : β>α=1/2 \\ σ_{n+1} & : α>1/2. \end{cases} $$ In the proofs we use a comparison result for Gaussian processes à la Gordon, exponential estimates for sums of chi-squared random variables, and estimates for the extreme singular values of (structured) Gaussian random matrices. The upper bound is constructive. It is proven for the worst case error of a least squares estimator.
format Preprint
id arxiv_https___arxiv_org_abs_1901_06639
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Random sections of ellipsoids and the power of random information
Hinrichs, Aicke
Krieg, David
Novak, Erich
Prochno, Joscha
Ullrich, Mario
Functional Analysis
Numerical Analysis
Metric Geometry
Probability
Primary: 42B35, 52A23, 65Y20 Secondary: 65D15, 60B20, 60G15
We study the circumradius of the intersection of an $m$-dimensional ellipsoid $\mathcal E$ with semi-axes $σ_1\geq\dots\geq σ_m$ with random subspaces of codimension $n$. We find that, under certain assumptions on $σ$, this random radius $\mathcal{R}_n=\mathcal{R}_n(σ)$ is of the same order as the minimal such radius $σ_{n+1}$ with high probability. In other situations $\mathcal{R}_n$ is close to the maximum $σ_1$. The random variable $\mathcal{R}_n$ naturally corresponds to the worst-case error of the best algorithm based on random information for $L_2$-approximation of functions from a compactly embedded Hilbert space $H$ with unit ball $\mathcal E$. In particular, $σ_k$ is the $k$th largest singular value of the embedding $H\hookrightarrow L_2$. In this formulation, one can also consider the case $m=\infty$, and we prove that random information behaves very differently depending on whether $σ\in \ell_2$ or not. For $σ\notin \ell_2$ random information is completely useless, i.e., $\mathbb E[\mathcal{R}_n] = σ_1$. For $σ\in \ell_2$ the expected radius of random information tends to zero at least at rate $o(1/\sqrt{n})$ as $n\to\infty$. In the important case $σ_k \asymp k^{-α} \ln^{-β}(k+1)$, where $α> 0$ and $β\in\mathbb R$, we obtain that $$ \mathbb E [\mathcal{R}_n(σ)] \asymp \begin{cases} σ_1 & : α<1/2 \,\text{ or }\, β\leqα=1/2 \\ σ_n \, \sqrt{\ln(n+1)} & : β>α=1/2 \\ σ_{n+1} & : α>1/2. \end{cases} $$ In the proofs we use a comparison result for Gaussian processes à la Gordon, exponential estimates for sums of chi-squared random variables, and estimates for the extreme singular values of (structured) Gaussian random matrices. The upper bound is constructive. It is proven for the worst case error of a least squares estimator.
title Random sections of ellipsoids and the power of random information
topic Functional Analysis
Numerical Analysis
Metric Geometry
Probability
Primary: 42B35, 52A23, 65Y20 Secondary: 65D15, 60B20, 60G15
url https://arxiv.org/abs/1901.06639