On -families of probability distributions
Abstract
We generalize the exponential family of probability distributions. In our approach, the exponential function is replaced by a -function, resulting in a -family of probability distributions. We show how -families are constructed. In a -family, the analogue of the cumulant-generating function is a normalizing function. We define the -divergence as the Bregman divergence associated to the normalizing function, providing a generalization of the Kullback-Leibler divergence. A formula for the -divergence where the -function is the Kaniadakis' -exponential function is derived.
Turn this paper into a lesson
ArcXiv compiles a structured reading guide from this paper's metadata: plain-English importance, contributions, prerequisite concepts, which sections to read first, flashcards, and a quiz. Grounded in the abstract, never invented.