Recently, Balcan and Blum [1] suggested a theory of learning based on general similarity functions, instead of positive semi-definite kernels. We study the gap between the learnin...
We give an algorithm for the on-line learning of permutations. The algorithm maintains its uncertainty about the target permutation as a doubly stochastic weight matrix, and makes...
When comparing discrete probability distributions, natural measures of similarity are not p distances but rather are informationdivergences such as Kullback-Leibler and Hellinger. ...
Abstract. We establish a generic theoretical tool to construct probabilistic bounds for algorithms where the output is a subset of objects from an initial pool of candidates (or mo...
Abstract. We propose simple randomized strategies for sequential prediction under imperfect monitoring, that is, when the forecaster does not have access to the past outcomes but r...