A method to construct exponential families by representation theory

11/04/2018
by   Koichi Tojo, et al.
0

In this paper, we give a method to construct "good" exponential families systematically by representation theory. More precisely, we consider a homogeneous space G/H as a sample space and construct a exponential family invariant under the transformation group G by using a representation of G. The method generates widely used exponential families such as normal, gamma, Bernoulli, categorical, Wishart, von Mises and Fisher-Bingham distributions. Moreover, we obtain a new family of distributions on the upper half plane compatible with the Poincaré metric.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/06/2019

On a method to construct exponential families by representation theory

Exponential family plays an important role in information geometry. In a...
research
12/13/2021

A Complete Characterisation of ReLU-Invariant Distributions

We give a complete characterisation of families of probability distribut...
research
02/07/2018

Wishart laws and variance function on homogeneous cones

We present a systematic study of Riesz measures and their natural expone...
research
05/27/2022

Information geometry of the Tojo-Yoshino's exponential family on the Poincaré upper plane

We study the dually flat information geometry of the Tojo-Yoshino expone...
research
08/04/2021

Sparse Continuous Distributions and Fenchel-Young Losses

Exponential families are widely used in machine learning; they include m...
research
05/19/2013

Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families

We study online learning under logarithmic loss with regular parametric ...
research
08/01/2010

Mixture decompositions of exponential families using a decomposition of their sample spaces

We study the problem of finding the smallest m such that every element o...

Please sign up or login with your details

Forgot password? Click here to reset