Least squares approximations in linear statistical inverse learning problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Helin, Tapio
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911760539189248
author Helin, Tapio
author_facet Helin, Tapio
contents Statistical inverse learning aims at recovering an unknown function $f$ from randomly scattered and possibly noisy point evaluations of another function $g$, connected to $f$ via an ill-posed mathematical model. In this paper we blend statistical inverse learning theory with the classical regularization strategy of applying finite-dimensional projections. Our key finding is that coupling the number of random point evaluations with the choice of projection dimension, one can derive probabilistic convergence rates for the reconstruction error of the maximum likelihood (ML) estimator. Convergence rates in expectation are derived with a ML estimator complemented with a norm-based cut-off operation. Moreover, we prove that the obtained rates are minimax optimal.
format Preprint
id arxiv_https___arxiv_org_abs_2211_12121
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Least squares approximations in linear statistical inverse learning problems
Helin, Tapio
Statistics Theory
Numerical Analysis
62G08, 62G20, 65J20, 68Q32
Statistical inverse learning aims at recovering an unknown function $f$ from randomly scattered and possibly noisy point evaluations of another function $g$, connected to $f$ via an ill-posed mathematical model. In this paper we blend statistical inverse learning theory with the classical regularization strategy of applying finite-dimensional projections. Our key finding is that coupling the number of random point evaluations with the choice of projection dimension, one can derive probabilistic convergence rates for the reconstruction error of the maximum likelihood (ML) estimator. Convergence rates in expectation are derived with a ML estimator complemented with a norm-based cut-off operation. Moreover, we prove that the obtained rates are minimax optimal.
title Least squares approximations in linear statistical inverse learning problems
topic Statistics Theory
Numerical Analysis
62G08, 62G20, 65J20, 68Q32
url https://arxiv.org/abs/2211.12121