Convex learning of multiple tasks and their structure
Name
1504.03101.pdf
Size
297.97 KB
Format
Adobe PDF
Checksum (MD5)
75e7b06d1158369ef82291904d2321f3
Author(s)
Ciliberto, Carlo
Mroueh, Youssef
Poggio, Tomaso A
Rosasco, Lorenzo
Date Issued
July 2015
Journal
Journal of Machine Learning Research
Publisher
MIT Press
Citation
Ciliberto, Carlo et al. "Convex learning of multiple tasks and their structure." Journal of Machine Learning Research, Proceedings of the 32nd International Conference on Machine Learning, July 7-9 2015, Lille, France, MIT Press, July 2015 Copyright © 2015 The Author(s)
Version
Author's final manuscript
Abstract
Reducing the amount of human supervision is a key problem in machine learning and a natural approach is that of exploiting the relations (structure) among different tasks. This is the idea at the core of multi-task learning. In this context a fundamental question is how to incorporate the tasks structure in the learning problem. We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches. Within this framework, we show that tasks and their structure can be efficiently learned considering a convex optimization problem that can be approached by means of block coordinate methods such as alternating minimization and for which we prove convergence to the global minimum.
MIT Department
Center for Brains, Minds, and Machines
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://dl.acm.org/citation.cfm?id=3045283
