Vector-Valued Least-Squares Regression under Output Regularity Assumptions
Loading...
Access rights
openAccess
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2022
Major/Subject
Mcode
Degree programme
Language
en
Pages
50
1-50
1-50
Series
Journal of Machine Learning Research, Volume 23
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.Description
Keywords
Other note
Citation
Brogat-Motte , L , Rudi , A , Brouard , C , Rousu , J & d'Alché-Buc , F 2022 , ' Vector-Valued Least-Squares Regression under Output Regularity Assumptions ' , Journal of Machine Learning Research , vol. 23 , 344 , pp. 1-50 . < https://www.jmlr.org/papers/v23/21-1357.html >