Matrix regularization techniques for online multitask learning
Agarwal, Alekh, Rakhlin, Alexander, & Bartlett, Peter (2008) Matrix regularization techniques for online multitask learning. Technical Report, UCB/EECS-2008-138. University of California, Berkeley, Calif..
In this paper we examine the problem of prediction with expert advice in a setup where the learner is presented with a sequence of examples coming from different tasks. In order for the learner to be able to benefit from performing multiple tasks simultaneously, we make assumptions of task relatedness by constraining the comparator to use a lesser number of best experts than the number of tasks. We show how this corresponds naturally to learning under spectral or structural matrix constraints, and propose regularization techniques to enforce the constraints. The regularization techniques proposed here are interesting in their own right and multitask learning is just one application for the ideas. A theoretical analysis of one such regularizer is performed, and a regret bound that shows benefits of this setup is reported.
Impact and interest:
Citation counts are sourced monthly from and citation databases.
These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
|Additional Information:||Fulltext freely available see link above|
|Divisions:||Past > QUT Faculties & Divisions > Faculty of Science and Technology
Past > Schools > Mathematical Sciences
|Copyright Owner:||Copyright 2008 please consult the authors|
|Deposited On:||17 Aug 2011 23:58|
|Last Modified:||23 Jan 2015 04:30|
Repository Staff Only: item control page