Dynamic Mixture Ratio Model

Finite mixtures of probability densities with components from exponential family serve as flexible parametric models of high-dimensional systems. However, with a few specialized exceptions, these dynamic models assume data-independent weights of mixture components. Their use is illogical and restricts the modeling applicability. The requirement for closeness with respect to conditioning, the basic learning operation, leads to a novel class of models: the mixture ratios. The paper justified them and shows their ability to model truly dynamic systems.