We are concerned with the problem of sequential prediction using a givenhypothesis class of continuously-manyprediction strategies. An eectiveperformance measure is the minimax re...
We analyze the regret, measured in terms of log loss, of the maximum likelihood (ML) sequential prediction strategy. This "follow the leader" strategy also defines one o...
In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
Background: Bacterial promoters, which increase the efficiency of gene expression, differ from other promoters by several characteristics. This difference, not yet widely exploite...