Vector-Valued Least-Squares Regression under Output Regularity Assumptions - Archive ouverte HAL Access content directly
Journal Articles Journal of Machine Learning Research Year : 2022

Vector-Valued Least-Squares Regression under Output Regularity Assumptions

(1, 2, 3) , (4, 5) , (6) , (7) , (1, 2, 3)
1
2
3
4
5
6
7

Abstract

We propose and analyse a reduced-rank method for solving least-squares regression problems with infinite dimensional output. We derive learning bounds for our method, and study under which setting statistical performance is improved in comparison to full-rank method. Our analysis extends the interest of reduced-rank regression beyond the standard low-rank setting to more general output regularity assumptions. We illustrate our theoretical insights on synthetic least-squares problems. Then, we propose a surrogate structured prediction method derived from this reduced-rank method. We assess its benefits on three different problems: image reconstruction, multi-label classification, and metabolite identification.
Fichier principal
Vignette du fichier
21-1357.pdf (675.23 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-03888760 , version 1 (08-12-2022)

Identifiers

  • HAL Id : hal-03888760 , version 1

Cite

Luc Brogat-Motte, Alessandro Rudi, Céline Brouard, Juho Rousu, Florence d'Alché-Buc. Vector-Valued Least-Squares Regression under Output Regularity Assumptions. Journal of Machine Learning Research, 2022. ⟨hal-03888760⟩
0 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More