Iterative regularization in classification via hinge loss diagonal descent

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Apidopoulos, Vassilis, Poggio, Tomaso, Rosasco, Lorenzo, Villa, Silvia
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910639265415168
author Apidopoulos, Vassilis
Poggio, Tomaso
Rosasco, Lorenzo
Villa, Silvia
author_facet Apidopoulos, Vassilis
Poggio, Tomaso
Rosasco, Lorenzo
Villa, Silvia
contents Iterative regularization is a classic idea in regularization theory, that has recently become popular in machine learning. On the one hand, it allows to design efficient algorithms controlling at the same time numerical and statistical accuracy. On the other hand it allows to shed light on the learning curves observed while training neural networks. In this paper, we focus on iterative regularization in the context of classification. After contrasting this setting with that of linear inverse problems, we develop an iterative regularization approach based on the use of the hinge loss function. More precisely we consider a diagonal approach for a family of algorithms for which we prove convergence as well as rates of convergence and stability results for a suitable classification noise model. Our approach compares favorably with other alternatives, as confirmed by numerical simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2212_12675
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Iterative regularization in classification via hinge loss diagonal descent
Apidopoulos, Vassilis
Poggio, Tomaso
Rosasco, Lorenzo
Villa, Silvia
Machine Learning
Optimization and Control
Iterative regularization is a classic idea in regularization theory, that has recently become popular in machine learning. On the one hand, it allows to design efficient algorithms controlling at the same time numerical and statistical accuracy. On the other hand it allows to shed light on the learning curves observed while training neural networks. In this paper, we focus on iterative regularization in the context of classification. After contrasting this setting with that of linear inverse problems, we develop an iterative regularization approach based on the use of the hinge loss function. More precisely we consider a diagonal approach for a family of algorithms for which we prove convergence as well as rates of convergence and stability results for a suitable classification noise model. Our approach compares favorably with other alternatives, as confirmed by numerical simulations.
title Iterative regularization in classification via hinge loss diagonal descent
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2212.12675