Online Multi-task Learning with Hard Constraints

Simple item page
dc.creatorLugosi, Gabor
dc.creatorPapaspiliopoulos, Omiros
dc.creatorStoltz, Gilles
dc.date2009-02-20
dc.date2009-03-27
dc.date.accessioned2026-07-07T12:56:55Z
dc.date.available2026-07-07T12:56:55Z
dc.descriptionWe 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.
dc.identifierhttps://arxiv.org/abs/0902.3526
dc.identifierhttp://arxiv.org/abs/0902.3526
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/224748
dc.subjectMachine Learning
dc.subjectStatistics Theory
dc.titleOnline Multi-task Learning with Hard Constraints
dc.typetext

Files

Collections

arXiv