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).

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.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:5050
Deposited By:Omiros Papaspiliopoulos
Deposited On:24 March 2009