Key to multitask learning is exploiting the relationships between different tasks inorder to improve prediction performance. Most previous methods have focused onthe case where tasks relations can be modeled as linear operators and regularizationapproaches can be used successfully. However, in practice assuming the tasks tobe linearly related is often restrictive, and allowing for nonlinear structures is achallenge. In this paper, we tackle this issue by casting the problem within theframework of structured prediction. Our main contribution is a novel algorithm forlearning multiple tasks which are related by a system of nonlinear equations thattheir joint outputs need to satisfy. We show that our algorithm can be efficientlyimplemented and study its generalization properties, proving universal consistencyand learning rates. Our theoretical analysis highlights the benefits of non-linearmultitask learning over learning the tasks independently. Encouraging experimentalresults show the benefits of the proposed method in practice.

Consistent Multitask Learning with Nonlinear Output Relations

Carlo Ciliberto;Alessandro Rudi;Lorenzo Rosasco;
2017

Abstract

Key to multitask learning is exploiting the relationships between different tasks inorder to improve prediction performance. Most previous methods have focused onthe case where tasks relations can be modeled as linear operators and regularizationapproaches can be used successfully. However, in practice assuming the tasks tobe linearly related is often restrictive, and allowing for nonlinear structures is achallenge. In this paper, we tackle this issue by casting the problem within theframework of structured prediction. Our main contribution is a novel algorithm forlearning multiple tasks which are related by a system of nonlinear equations thattheir joint outputs need to satisfy. We show that our algorithm can be efficientlyimplemented and study its generalization properties, proving universal consistencyand learning rates. Our theoretical analysis highlights the benefits of non-linearmultitask learning over learning the tasks independently. Encouraging experimentalresults show the benefits of the proposed method in practice.
File in questo prodotto:
File Dimensione Formato  
Consistent Multitask.pdf

accesso aperto

Tipologia: Documento in Post-print
Dimensione 655.62 kB
Formato Adobe PDF
655.62 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/888667
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact