This paper analyzes the potential advantages and theoretical challenges of “active learning” algorithms. Active learning involves sequential sampling procedures that use infor...
We study the problem of active learning with convex loss functions. We prove that even under bounded noise constraints, the minimax rates for proper active learning are often no b...
We are concerned with the problem of sequential prediction using a givenhypothesis class of continuously-manyprediction strategies. An eectiveperformance measure is the minimax re...
Abstract. We consider a problem that is related to the “Universal Encoding Problem” from information theory. The basic goal is to find rules that map “partial information”...
Abstract. We derive upper and lower bounds for some statistical estimation problems. The upper bounds are established for the Gibbs algorithm. The lower bounds, applicable for all ...