Normal view MARC view

Convex multi-task feature learning

Author: Argyriou, Andreas ; Evgeniou, Theodoros ; Pontil, MassimilianoINSEAD Area: Technology and Operations ManagementIn: Machine Learning, vol. 73, no. 3, December 2008 Language: EnglishDescription: p. 243-272.Type of document: INSEAD ArticleNote: Please ask us for this itemAbstract: We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the well-known single task 1-norm regularization. It is based on a novel non-convex regularizer which controls the number of learned features common across the tasks. We prove that the method is equivalent to solving a convex optimization problem for which there is an iterative algorithm which, as we prove, converges to an optimal solution. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the former step it learns task-specific functions and in the latter step it learns common-across tasks sparse representations for these functions. We also provide an extension of the algorithm which learns sparse nonlinear representations using kernels. We report experiments on simulated and real data sets which demonstrate that the proposed method can both improve the performance relative to learning each task independently and lead to a few learned features common across related tasks. Our algorithm can also be used, as a special case, to simply select, not learn, a few common variables across the tasks.
Tags: No tags from this library for this title. Log in to add tags.
Item type Current location Call number Status Date due Barcode Item holds
INSEAD Article Europe Campus
Available BC008467
Total holds: 0

Ask Qualtrics

We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the well-known single task 1-norm regularization. It is based on a novel non-convex regularizer which controls the number of learned features common across the tasks. We prove that the method is equivalent to solving a convex optimization problem for which there is an iterative algorithm which, as we prove, converges to an optimal solution. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the former step it learns task-specific functions and in the latter step it learns common-across tasks sparse representations for these functions. We also provide an extension of the algorithm which learns sparse nonlinear representations using kernels. We report experiments on simulated and real data sets which demonstrate that the proposed method can both improve the performance relative to learning each task independently and lead to a few learned features common across related tasks. Our algorithm can also be used, as a special case, to simply select, not learn, a few common variables across the tasks.

Digitized

There are no comments for this item.

Log in to your account to post a comment.
Koha 18.11 - INSEAD Catalogue
Home | Contact Us | What's Koha?