On Monotone Embedding in Information Geometry

A paper was published (Harsha and Subrahamanian Moosath, 2014) in which the authors claimed to have discovered an extension to Amari's \(\alpha\)-geometry through a general monotone embedding function. It will be pointed out here that this so-called \((F, G)\)-geometry (which includes \(F\)-geo...

Full description

Bibliographic Details
Main Author: Jun Zhang
Format: Article
Language:English
Published: MDPI AG 2015-06-01
Series:Entropy
Subjects:
Online Access:http://www.mdpi.com/1099-4300/17/7/4485
_version_ 1828283625743843328
author Jun Zhang
author_facet Jun Zhang
author_sort Jun Zhang
collection DOAJ
description A paper was published (Harsha and Subrahamanian Moosath, 2014) in which the authors claimed to have discovered an extension to Amari's \(\alpha\)-geometry through a general monotone embedding function. It will be pointed out here that this so-called \((F, G)\)-geometry (which includes \(F\)-geometry as a special case) is identical to Zhang's (2004) extension to the \(\alpha\)-geometry, where the name of the pair of monotone embedding functions \(\rho\) and \(\tau\) were used instead of \(F\) and \(H\) used in Harsha and Subrahamanian Moosath (2014). Their weighting function \(G\) for the Riemannian metric appears cosmetically due to a rewrite of the score function in log-representation as opposed to \((\rho, \tau)\)-representation in Zhang (2004). It is further shown here that the resulting metric and \(\alpha\)-connections obtained by Zhang (2004) through arbitrary monotone embeddings is a unique extension of the \(\alpha\)-geometric structure. As a special case, Naudts' (2004) \(\phi\)-logarithm embedding (using the so-called \(\log_\phi\) function) is recovered with the identification \(\rho=\phi, \, \tau=\log_\phi\), with \(\phi\)-exponential \(\exp_\phi\) given by the associated convex function linking the two representations.
first_indexed 2024-04-13T08:48:09Z
format Article
id doaj.art-cd9c744fcfa04f73b0f95097f93e38f7
institution Directory Open Access Journal
issn 1099-4300
language English
last_indexed 2024-04-13T08:48:09Z
publishDate 2015-06-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj.art-cd9c744fcfa04f73b0f95097f93e38f72022-12-22T02:53:36ZengMDPI AGEntropy1099-43002015-06-011774485449910.3390/e17074485e17074485On Monotone Embedding in Information GeometryJun Zhang0Department of Psychology and Department of Mathematics, University of Michigan, 530 Church Street, Ann Arbor, MI 48109, USAA paper was published (Harsha and Subrahamanian Moosath, 2014) in which the authors claimed to have discovered an extension to Amari's \(\alpha\)-geometry through a general monotone embedding function. It will be pointed out here that this so-called \((F, G)\)-geometry (which includes \(F\)-geometry as a special case) is identical to Zhang's (2004) extension to the \(\alpha\)-geometry, where the name of the pair of monotone embedding functions \(\rho\) and \(\tau\) were used instead of \(F\) and \(H\) used in Harsha and Subrahamanian Moosath (2014). Their weighting function \(G\) for the Riemannian metric appears cosmetically due to a rewrite of the score function in log-representation as opposed to \((\rho, \tau)\)-representation in Zhang (2004). It is further shown here that the resulting metric and \(\alpha\)-connections obtained by Zhang (2004) through arbitrary monotone embeddings is a unique extension of the \(\alpha\)-geometric structure. As a special case, Naudts' (2004) \(\phi\)-logarithm embedding (using the so-called \(\log_\phi\) function) is recovered with the identification \(\rho=\phi, \, \tau=\log_\phi\), with \(\phi\)-exponential \(\exp_\phi\) given by the associated convex function linking the two representations.http://www.mdpi.com/1099-4300/17/7/4485α-embeddingmonotone embeddingconjugate embeddinggeneralized Fisher–Rao metricAmari–Chentsov tensordeformed logarithmrepresentation duality(ρ,τ)-geometry
spellingShingle Jun Zhang
On Monotone Embedding in Information Geometry
Entropy
α-embedding
monotone embedding
conjugate embedding
generalized Fisher–Rao metric
Amari–Chentsov tensor
deformed logarithm
representation duality
(ρ,τ)-geometry
title On Monotone Embedding in Information Geometry
title_full On Monotone Embedding in Information Geometry
title_fullStr On Monotone Embedding in Information Geometry
title_full_unstemmed On Monotone Embedding in Information Geometry
title_short On Monotone Embedding in Information Geometry
title_sort on monotone embedding in information geometry
topic α-embedding
monotone embedding
conjugate embedding
generalized Fisher–Rao metric
Amari–Chentsov tensor
deformed logarithm
representation duality
(ρ,τ)-geometry
url http://www.mdpi.com/1099-4300/17/7/4485
work_keys_str_mv AT junzhang onmonotoneembeddingininformationgeometry