
TL;DR
This paper introduces a generalized form of beta divergence using a compact integral representation, simplifying property derivations and establishing its equivalence with statistical deviance.
Contribution
It extends beta divergence beyond classical forms with a new integral representation, linking it to statistical deviance and simplifying analysis.
Findings
Generalized beta divergence expressed as a compact integral.
Simplified derivations of scaling, translation, and expectation properties.
Established equivalence between beta divergence and statistical deviance.
Abstract
This paper generalizes beta divergence beyond its classical form associated with power variance functions of Tweedie models. Generalized form is represented by a compact definite integral as a function of variance function of the exponential dispersion model. This compact integral form simplifies derivations of many properties such as scaling, translation and expectation of the beta divergence. Further, we show that beta divergence and (half of) the statistical deviance are equivalent measures.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsControl Systems and Identification · Probabilistic and Robust Engineering Design · Mathematical Approximation and Integration
