Abstract. We consider the framework of stochastic multi-armed bandit problems and study the possibilities and limitations of strategies that explore sequentially the arms. The stra...
Abstract. The nearest neighbor and the perceptron algorithms are intuitively motivated by the aims to exploit the “cluster” and “linear separation” structure of the data to...
Abstract. We propose a thresholded ensemble model for ordinal regression problems. The model consists of a weighted ensemble of confidence functions and an ordered vector of thres...
Abstract. We describe and analyze an algorithm for predicting a sequence of n-dimensional binary vectors based on a set of experts making vector predictions in [0, 1]n . We measure...
Matthew Henderson, John Shawe-Taylor, Janez Zerovn...
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...