Symplectic Bregman Divergences

We present a generalization of Bregman divergences in finite-dimensional symplectic vector spaces that we term symplectic Bregman divergences. Symplectic Bregman divergences are derived from a symplectic generalization of the Fenchel–Young inequality which relies on the notion of symplectic subdiffe...

Full description

Saved in:
Bibliographic Details
Main Author: Frank Nielsen
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/26/12/1101
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104700560080896
author Frank Nielsen
author_facet Frank Nielsen
author_sort Frank Nielsen
collection DOAJ
description We present a generalization of Bregman divergences in finite-dimensional symplectic vector spaces that we term symplectic Bregman divergences. Symplectic Bregman divergences are derived from a symplectic generalization of the Fenchel–Young inequality which relies on the notion of symplectic subdifferentials. The symplectic Fenchel–Young inequality is obtained using the symplectic Fenchel transform which is defined with respect to the symplectic form. Since symplectic forms can be built generically from pairings of dual systems, we obtain a generalization of Bregman divergences in dual systems obtained by equivalent symplectic Bregman divergences. In particular, when the symplectic form is derived from an inner product, we show that the corresponding symplectic Bregman divergences amount to ordinary Bregman divergences with respect to composite inner products. Some potential applications of symplectic divergences in geometric mechanics, information geometry, and learning dynamics in machine learning are touched upon.
format Article
id doaj-art-3b94c0f96fd5413aa1c53b8ae28f5f56
institution Kabale University
issn 1099-4300
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-3b94c0f96fd5413aa1c53b8ae28f5f562024-12-27T14:25:12ZengMDPI AGEntropy1099-43002024-12-012612110110.3390/e26121101Symplectic Bregman DivergencesFrank Nielsen0Sony Computer Science Laboratories Inc., Tokyo 141-0022, JapanWe present a generalization of Bregman divergences in finite-dimensional symplectic vector spaces that we term symplectic Bregman divergences. Symplectic Bregman divergences are derived from a symplectic generalization of the Fenchel–Young inequality which relies on the notion of symplectic subdifferentials. The symplectic Fenchel–Young inequality is obtained using the symplectic Fenchel transform which is defined with respect to the symplectic form. Since symplectic forms can be built generically from pairings of dual systems, we obtain a generalization of Bregman divergences in dual systems obtained by equivalent symplectic Bregman divergences. In particular, when the symplectic form is derived from an inner product, we show that the corresponding symplectic Bregman divergences amount to ordinary Bregman divergences with respect to composite inner products. Some potential applications of symplectic divergences in geometric mechanics, information geometry, and learning dynamics in machine learning are touched upon.https://www.mdpi.com/1099-4300/26/12/1101dual systemduality productinner productsymplectic formsymplectic matrix groupsymplectic subdifferential
spellingShingle Frank Nielsen
Symplectic Bregman Divergences
Entropy
dual system
duality product
inner product
symplectic form
symplectic matrix group
symplectic subdifferential
title Symplectic Bregman Divergences
title_full Symplectic Bregman Divergences
title_fullStr Symplectic Bregman Divergences
title_full_unstemmed Symplectic Bregman Divergences
title_short Symplectic Bregman Divergences
title_sort symplectic bregman divergences
topic dual system
duality product
inner product
symplectic form
symplectic matrix group
symplectic subdifferential
url https://www.mdpi.com/1099-4300/26/12/1101
work_keys_str_mv AT franknielsen symplecticbregmandivergences