Saved in:
Bibliographic Details
Main Authors: Omiya, Gaku, Komaki, Fumiyasu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.09358
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909953685454848
author Omiya, Gaku
Komaki, Fumiyasu
author_facet Omiya, Gaku
Komaki, Fumiyasu
contents We propose geodesic-based optimization methods on dually flat spaces, where the geometric structure of the parameter manifold is closely related to the form of the objective function. A primary application is maximum likelihood estimation in statistical models, especially exponential families, whose model manifolds are dually flat. We show that an m-geodesic update, which directly optimizes the log-likelihood, can theoretically reach the maximum likelihood estimator in a single step. In contrast, an e-geodesic update has a practical advantage in cases where the parameter space is geodesically complete, allowing optimization without explicitly handling parameter constraints. We establish the theoretical properties of the proposed methods and validate their effectiveness through numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Minimization of Functions on Dually Flat Spaces Using Geodesic Descent Based on Dual Connections
Omiya, Gaku
Komaki, Fumiyasu
Computation
Machine Learning
53C20, 62F10(Secondary), 90C30(Primary)
We propose geodesic-based optimization methods on dually flat spaces, where the geometric structure of the parameter manifold is closely related to the form of the objective function. A primary application is maximum likelihood estimation in statistical models, especially exponential families, whose model manifolds are dually flat. We show that an m-geodesic update, which directly optimizes the log-likelihood, can theoretically reach the maximum likelihood estimator in a single step. In contrast, an e-geodesic update has a practical advantage in cases where the parameter space is geodesically complete, allowing optimization without explicitly handling parameter constraints. We establish the theoretical properties of the proposed methods and validate their effectiveness through numerical experiments.
title Minimization of Functions on Dually Flat Spaces Using Geodesic Descent Based on Dual Connections
topic Computation
Machine Learning
53C20, 62F10(Secondary), 90C30(Primary)
url https://arxiv.org/abs/2512.09358