Compositional data, i.e. data including only relative information, need to be transformed prior to applying the standard discriminant analysis methods that are designed for the Euclidean space. Here it is investigated for linear, quadratic, and Fisher discriminant analysis, which of the...

Nearest neighbour classification requires a good distance metric. Previous approaches try to learn a quadratic distance metric learning so that observations of different classes are well separated. For high-dimensional problems, where many uninformative variables are present, it is attractive to...

In this article a new value for positive cooperative games is introduced. It generalizes the “proportional division of surplus” idea for two person games. A characterization by means of preservation of ratios and efficiency provides existence and uniqueness. Moreover, this value is the only...