PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Online Multi-task Learning with Hard Constraints
Gábor Lugosi, Omiros Papaspiliopoulos and Gilles Stoltz
In: COLT 2009, June 2009, Montreal, Canada.


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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Theory & Algorithms
ID Code:4564
Deposited By:Gilles Stoltz
Deposited On:13 March 2009