Online Multi-task Learning with Hard Constraints
Machine Learning
2009-03-27 v2 Machine Learning
Statistics Theory
Statistics Theory
Abstract
We discuss multi-task online learning when a decision maker has to deal simultaneously with M tasks. The tasks are related, which is modeled by imposing that the M-tuple of actions taken by the decision maker needs to satisfy certain constraints. We give natural examples of such restrictions and then discuss a general class of tractable constraints, for which we introduce computationally efficient ways of selecting actions, essentially by reducing to an on-line shortest path problem. We briefly discuss "tracking" and "bandit" versions of the problem and extend the model in various ways, including non-additive global losses and uncountably infinite sets of tasks.
Cite
@article{arxiv.0902.3526,
title = {Online Multi-task Learning with Hard Constraints},
author = {Gabor Lugosi and Omiros Papaspiliopoulos and Gilles Stoltz},
journal= {arXiv preprint arXiv:0902.3526},
year = {2009}
}