We study on-line play of repeated matrix games in which the observations of past actions of the other player and the obtained reward are partial and stochastic. We define the Part...
In this paper the sequential prediction problem with expert advice is considered when the loss is unbounded under partial monitoring scenarios. We deal with a wide class of the par...
Abstract. Active Shape Models are commonly used to recognize and locate different aspects of known rigid objects. However, they require an off-line learning stage, such that the ex...
Michael Fussenegger, Peter M. Roth, Horst Bischof,...
The majority of theoretical work in machine learning is done under the assumption of exchangeability: essentially, it is assumed that the examples are generated from the same prob...
Vladimir Vovk, Ilia Nouretdinov, Alexander Gammerm...
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...