Salvato in:
Dettagli Bibliografici
Autori principali: Magnani, Emilia, De Vito, Ernesto, Hennig, Philipp, Rosasco, Lorenzo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2501.05279
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916682280206336
author Magnani, Emilia
De Vito, Ernesto
Hennig, Philipp
Rosasco, Lorenzo
author_facet Magnani, Emilia
De Vito, Ernesto
Hennig, Philipp
Rosasco, Lorenzo
contents We consider the problem of learning convolution operators associated to compact Abelian groups. We study a regularization-based approach and provide corresponding learning guarantees under natural regularity conditions on the convolution kernel. More precisely, we assume the convolution kernel is a function in a translation invariant Hilbert space and analyze a natural ridge regression (RR) estimator. Building on existing results for RR, we characterize the accuracy of the estimator in terms of finite sample bounds. Interestingly, regularity assumptions which are classical in the analysis of RR, have a novel and natural interpretation in terms of space/frequency localization. Theoretical results are illustrated by numerical simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning convolution operators on compact Abelian groups
Magnani, Emilia
De Vito, Ernesto
Hennig, Philipp
Rosasco, Lorenzo
Machine Learning
68T05, 47A52, 42B10, 62J07
I.2.6; F.2.1; G.3
We consider the problem of learning convolution operators associated to compact Abelian groups. We study a regularization-based approach and provide corresponding learning guarantees under natural regularity conditions on the convolution kernel. More precisely, we assume the convolution kernel is a function in a translation invariant Hilbert space and analyze a natural ridge regression (RR) estimator. Building on existing results for RR, we characterize the accuracy of the estimator in terms of finite sample bounds. Interestingly, regularity assumptions which are classical in the analysis of RR, have a novel and natural interpretation in terms of space/frequency localization. Theoretical results are illustrated by numerical simulations.
title Learning convolution operators on compact Abelian groups
topic Machine Learning
68T05, 47A52, 42B10, 62J07
I.2.6; F.2.1; G.3
url https://arxiv.org/abs/2501.05279