stat.MLNov 13, 2026

Bregman geometry in regular exponential families: dual representations and relative smoothness

Authors: Mame Diarra Fall, Éric Barat, Nicolas Dobigeon

Organizations: Univ. Rouen Normandie, LITIS, Rouen, France · Univ. Paris-Saclay, CEA, List, Palaiseau, France · Univ. Toulouse, IRIT/INP-ENSEEIHT, Toulouse, France

Abstract

Regular exponential-family distributions are ubiquitous in statistics due to their appealing and convenient properties. Notably, they can be expressed in terms of Bregman divergences, revealing fundamental connections between statistics, convex analysis, and information geometry. However, this geometric structure has not been systematically exploited to characterize these distributions with respect to their expectation parametrization. Building on a projective characterization, we establish a general construction of equivalent dual Bregman representations, together with normalization and uniqueness results. These representations express log-densities as ordinary Bregman divergences in dual coordinate systems, providing geometric characterizations of the parameter space. So-called ββ- and αα-scaled dual representations emerge as particular instances of this framework. We further derive dual Bregman representations of conjugate priors and establish that they preserve conjugacy. Applications to classical distributions illustrate the geometric structures underlying seemingly different statistical models. Moreover, we show that these representations provide natural reference geometries for establishing relative smoothness of the primal Bregman representation of the distribution, with explicit bounds that are sharp in the scalar and separable settings. An illustrative application to the Poisson distribution sheds new light on several works in the literature, providing complementary geometric justifications for reference geometries while deriving existing algorithms.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. The Bayesian Learning Rule Beyond KL Geometry

    Oct 22, 2026Sophia Sklaviadis, Wu Lin, Andre Martins +3Bayesian InferenceVariational Inference

  2. Generalising maximum mean discrepancy: kernelised functional Bregman divergences

    Apr 27, 2026Russell Tsuchida, Frank NielsenKernel Mean EmbeddingsFunctional Bregman Divergences