On Learning the Optimal Regularization Parameter in Inverse Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rodriguez, Jonathan Chirinos, De Vito, Ernesto, Molinari, Cesare, Rosasco, Lorenzo, Villa, Silvia
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917029606326272
author Rodriguez, Jonathan Chirinos
De Vito, Ernesto
Molinari, Cesare
Rosasco, Lorenzo
Villa, Silvia
author_facet Rodriguez, Jonathan Chirinos
De Vito, Ernesto
Molinari, Cesare
Rosasco, Lorenzo
Villa, Silvia
contents Selecting the best regularization parameter in inverse problems is a classical and yet challenging problem. Recently, data-driven approaches have become popular to tackle this challenge. These approaches are appealing since they do require less a priori knowledge, but their theoretical analysis is limited. In this paper, we propose and study a statistical machine learning approach, based on empirical risk minimization. Our main contribution is a theoretical analysis, showing that, provided with enough data, this approach can reach sharp rates while being essentially adaptive to the noise and smoothness of the problem. Numerical simulations corroborate and illustrate the theoretical findings. Our results are a step towards grounding theoretically data-driven approaches to inverse problems.
format Preprint
id arxiv_https___arxiv_org_abs_2311_15845
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On Learning the Optimal Regularization Parameter in Inverse Problems
Rodriguez, Jonathan Chirinos
De Vito, Ernesto
Molinari, Cesare
Rosasco, Lorenzo
Villa, Silvia
Statistics Theory
Optimization and Control
65J20, 47N10, 65K10, 62G05
Selecting the best regularization parameter in inverse problems is a classical and yet challenging problem. Recently, data-driven approaches have become popular to tackle this challenge. These approaches are appealing since they do require less a priori knowledge, but their theoretical analysis is limited. In this paper, we propose and study a statistical machine learning approach, based on empirical risk minimization. Our main contribution is a theoretical analysis, showing that, provided with enough data, this approach can reach sharp rates while being essentially adaptive to the noise and smoothness of the problem. Numerical simulations corroborate and illustrate the theoretical findings. Our results are a step towards grounding theoretically data-driven approaches to inverse problems.
title On Learning the Optimal Regularization Parameter in Inverse Problems
topic Statistics Theory
Optimization and Control
65J20, 47N10, 65K10, 62G05
url https://arxiv.org/abs/2311.15845