On a method to construct exponential families by representation theory

07/06/2019
by   Koichi Tojo, et al.
0

Exponential family plays an important role in information geometry. In arXiv:1811.01394, we introduced a method to construct an exponential family P={p_θ}_θ∈Θ on a homogeneous space G/H from a pair (V,v_0). Here V is a representation of G and v_0 is an H-fixed vector in V. Then the following questions naturally arise: (Q1) when is the correspondence θ p_θ injective? (Q2) when do distinct pairs (V,v_0) and (V',v_0') generate the same family? In this paper, we answer these two questions (Theorems 1 and 2). Moreover, in Section 3, we consider the case (G,H)=(R_>0, {1}) with a certain representation on R^2. Then we see the family obtained by our method is essentially generalized inverse Gaussian distribution (GIG).

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset