On Multivariate Structures and Exhaustive Reductions
Abstract
Simplified representations of multivariate laws, and in particular those allowing one to decrease the dimension while preserving structural information, are of paramount importance in statistical analysis. This paper concerns the "theoretical premises" of simplification. We introduce a framework that allows us to specify as "partitions" of probability laws on a Euclidian space, we show how they can be generated via "partial orders," or "binary operation" and "noise classes." Moreover, the framework allows us to identify "simplified representations" that are guaranteed to be "exhaustive" with respect to such definitions, and might live in "lower dimensions."