This paper studies a meta-simplex concept and geometric embedding framework for multi-
population replicator dynamics. Central results are two embedding theorems which …

We propose a novel class of deep stochastic predictors for classifying metric data on graphs
within the PAC-Bayes risk certification paradigm. Classifiers are realized as linearly …

We introduce a novel generative model for the representation of joint probability distributions
of a possibly large number of discrete random variables. The approach uses measure …

We propose a novel class of deep stochastic predictors for classifying metric data on graphs
within the PAC‐Bayes risk certification paradigm. Classifiers are realized as linearly …

We propose a novel way of approximating energy-based models by randomizing the
parameters of assignment flows, a class of smooth dynamical data labeling systems. Our …

We propose a novel way of approximating energy-based models by randomizing the
parameters of assignment flows, a class of smooth dynamical data labeling systems. Our …