We are concerned with the problem of sequential prediction using a givenhypothesis class of continuously-manyprediction strategies. An eectiveperformance measure is the minimax re...
While most supervised machine learning models assume that training examples are sampled at random or adversarially, this article is concerned with models of learning from a cooper...
Sandra Zilles, Steffen Lange, Robert Holte, Martin...
Abstract. We consider the problem of learning a user's ordinal preferences on a multiattribute domain, assuming that her preferences are lexicographic. We introduce a general ...
We wish to increase the power of an arbitrary algorithm designed for non-degenerate input, by allowing it to execute on all inputs. We concentrate on in nitesimal symbolic perturba...
We introduce a new model for learning in the presence of noise, which we call the Nasty Noise model. This model generalizes previously considered models of learning with noise. Th...