Saved in:
Bibliographic Details
Main Authors: Rastogi, Abhishake, Mathé, Peter
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2002.10208
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909162418470912
author Rastogi, Abhishake
Mathé, Peter
author_facet Rastogi, Abhishake
Mathé, Peter
contents We study the linear ill-posed inverse problem with noisy data in the statistical learning setting. Approximate reconstructions from random noisy data are sought with general regularization schemes in Hilbert scale. We discuss the rates of convergence for the regularized solution under the prior assumptions and a certain link condition. We express the error in terms of certain distance functions. For regression functions with smoothness given in terms of source conditions the error bound can then be explicitly established.
format Preprint
id arxiv_https___arxiv_org_abs_2002_10208
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Inverse learning in Hilbert scales
Rastogi, Abhishake
Mathé, Peter
Statistics Theory
Machine Learning
62G20
We study the linear ill-posed inverse problem with noisy data in the statistical learning setting. Approximate reconstructions from random noisy data are sought with general regularization schemes in Hilbert scale. We discuss the rates of convergence for the regularized solution under the prior assumptions and a certain link condition. We express the error in terms of certain distance functions. For regression functions with smoothness given in terms of source conditions the error bound can then be explicitly established.
title Inverse learning in Hilbert scales
topic Statistics Theory
Machine Learning
62G20
url https://arxiv.org/abs/2002.10208