Combinatorial Online Prediction via Metarounding

Abstract

We consider online prediction problems of combinatorial concepts. Examples of such concepts include s-t paths, permutations, truth assignments, set covers, and so on. The goal of the online prediction algorithm is to compete with the best fixed combinatorial concept in hindsight. A generic approach to this problem is to design an online prediction algorithm using the corresponding offline (approximation) algorithm as an oracle. The current state-of-the art method, however, is not efficient enough. In this paper we propose a more efficient online prediction algorithm when the offline approximation algorithm has a guarantee of the integrality gap.KeywordsApproximation RatioTruth AssignmentRank AggregationEllipsoid MethodCombinatorial ConceptThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.