Information Geometric Duality of ϕ-Deformed Exponential Families

Abstract

In the world of generalized entropies-which, for example, play a role in physical systems with sub-and super-exponential phasespace growth per degree of freedom-there are two ways for implementing constraints in the maximum entropy principle: linear-and escort constraints. Both appear naturally in different contexts. Linear constraints appear e.g. in physical systems, when additional information about the system is available through higher moments. Escort distributions appear naturally in the context of multifractals and information geometry. It was shown recently that there exists a fundamental duality that relates both approaches on the basis of the corresponding deformed logarithms (deformed-log duality). Here we show that there exists another duality that arises in the context of information geometry, relating the Fisher information of φ-deformed exponential families that correspond to linear constraints (as studied by J. Naudts), with those that are based on escort constraints (as studied by S.-I. Amari). We explicitly demonstrate this information geometric duality for the case of (c, d)-entropy that covers all situations that are compatible with the first three Shannon-Khinchin axioms, and that include Shannon, Tsallis, Anteneodo-Plastino entropy, and many more as special cases. Finally, we discuss the relation between the deformed-log duality and the information geometric duality, and mention that the escort distributions arising in the two dualities are generally different and only coincide for the case of the Tsallis deformation.

Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning

“…Here, we should notice that we are not satisfied with only achieving the smoothing purpose but aim to develop a sparse optimal policy. To achieve this goal, we define a class of proximity functions based on the κ-logarithm function (Korbel et al, 2019), i.e., d(x) = xφ(x) = − x 2 log κ (x), where log κ (x) = 1 1−κ (x 1−κ − 1) for x > 0 and κ = 1. In this paper, we consider a special case when k = 0, and refer to the operator (3.3) as the proximal Bellman operator.…”

Information geometry of scaling expansions of non-exponentially growing configuration spaces

“…where the function Ψ (θ) is called the Massieu function and normalizes the distribution. As discussed in [26], there are two natural ways how to make a connection with the theory of information through the maximum entropy principle. The first is based on the maximization of the entropy functional under the linear (thermodynamic) constraints, the latter is based on a maximization under so-called escort (or geometric) constraints.…”

“…Alternatively, one can use the divergence of Csiszár type, but its information geometry is trivial, because it is conformal to ordinary Fisher information geometry, see e.g., Refs. [26,35]. Let us consider a parametric family of distributions p(θ).…”

“…Let us first denote l (c,d) (x) = log (c,d) (x) + r. Then the derivatives of log (c,d) can be expressed as (see also Ref. [26]):…”

Εφαρμογές Της Γεωμετρίας Της Πληροφορίας

“…Τέλος ας αναφερθεί ότι μετά τη δημοσίευση των άρθρων αυτής της διατριβής που αναφέρονται στην ενότητα (3), δημοσιεύθηκε το [41] ( 1)(( 1) 1) ( ) 2 (( 1) 1)log( )…”