Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bravetti, Alessandro, Ariza, Miguel Ángel García, Romero-Arias, José Roberto
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.00192
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914435850829824
author Bravetti, Alessandro
Ariza, Miguel Ángel García
Romero-Arias, José Roberto
author_facet Bravetti, Alessandro
Ariza, Miguel Ángel García
Romero-Arias, José Roberto
contents In dually flat manifolds, there is a deep connection between gradient flows and pregeodesics. This was one of the many important contributions of Amari to information geometry. In this paper, we extend the study of this relationship to general Riemannian manifolds. Our result does not impose conditions of flatness on the connection or symmetry on its non-metricity tensor, thus broadening the geometric setting beyond Hessian manifolds. Within this framework, we provide a criterion for comparing relaxation along two different gradient descent curves of a function, formulated in terms of the non-metricity tensor of a connection for which the gradient curves are pregeodesics. We use it to study Gaussian chains, whose relaxation trajectories coincide with gradient descent curves in the space of Gaussian distributions.Thus, we recover a recent result that establishes a universal asymmetry: warming up is faster than cooling down. Our work illustrates how geometric insights rooted in Amari's legacy offer new perspectives for optimization problems and stochastic processes.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00192
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gradient systems and asymmetric relaxations in view of Riemannian geometry
Bravetti, Alessandro
Ariza, Miguel Ángel García
Romero-Arias, José Roberto
Differential Geometry
Statistical Mechanics
Mathematical Physics
53B12, 53B05, 53B50
In dually flat manifolds, there is a deep connection between gradient flows and pregeodesics. This was one of the many important contributions of Amari to information geometry. In this paper, we extend the study of this relationship to general Riemannian manifolds. Our result does not impose conditions of flatness on the connection or symmetry on its non-metricity tensor, thus broadening the geometric setting beyond Hessian manifolds. Within this framework, we provide a criterion for comparing relaxation along two different gradient descent curves of a function, formulated in terms of the non-metricity tensor of a connection for which the gradient curves are pregeodesics. We use it to study Gaussian chains, whose relaxation trajectories coincide with gradient descent curves in the space of Gaussian distributions.Thus, we recover a recent result that establishes a universal asymmetry: warming up is faster than cooling down. Our work illustrates how geometric insights rooted in Amari's legacy offer new perspectives for optimization problems and stochastic processes.
title Gradient systems and asymmetric relaxations in view of Riemannian geometry
topic Differential Geometry
Statistical Mechanics
Mathematical Physics
53B12, 53B05, 53B50
url https://arxiv.org/abs/2604.00192