Several functions originating from Fisher–Rao geometry of Dirichlet distributions and involving polygamma functions

F Qi, RP Agarwal - Mathematics, 2023 - mdpi.com
In this paper, the authors review and survey some results published since 2020 about
(complete) monotonicity, inequalities, and their necessary and sufficient conditions for …

A brief overview and survey of the scientific work by Feng Qi

RP Agarwal, E Karapinar, M Kostić, J Cao, WS Du - Axioms, 2022 - mdpi.com
Axioms | Free Full-Text | A Brief Overview and Survey of the Scientific Work by Feng Qi Next
Article in Journal A Stable Generalized Finite Element Method Coupled with Deep Neural …

On closed-form expressions for the Fisher–Rao distance

HK Miyamoto, FCC Meneghetti, J Pinele… - Information Geometry, 2024 - Springer
Abstract The Fisher–Rao distance is the geodesic distance between probability distributions
in a statistical manifold equipped with the Fisher metric, which is a natural choice of …

Theoretically and computationally convenient geometries on full-rank correlation matrices

Y Thanwerdas, X Pennec - SIAM Journal on Matrix Analysis and Applications, 2022 - SIAM
In contrast to SPD matrices, few tools exist to perform Riemannian statistics on the open
elliptope of full-rank correlation matrices. The quotient-affine metric was recently built as the …

Decreasing properties of two ratios defined by three and four polygamma functions

F Qi - Comptes Rendus. Mathématique, 2022 - comptes-rendus.academie-sciences …
In the paper, by virtue of the convolution theorem for the Laplace transforms, with the aid of
three monotonicity rules for the ratios of two functions, of two definite integrals, and of two …

Lower bound of sectional curvature of Fisher–Rao manifold of beta distributions and complete monotonicity of functions involving polygamma functions

F Qi - Results in Mathematics, 2021 - Springer
In the paper, by virtue of convolution theorem for the Laplace transforms and analytic
techniques, the author finds necessary and sufficient conditions for complete monotonicity …

Riemannian and stratified geometries on covariance and correlation matrices

Y Thanwerdas - 2022 - hal.science
In many applications, the data can be represented by covariance matrices or correlation
matrices between several signals (EEG, MEG, fMRI), physical quantities (cells, genes), or …

Parametric information geometry with the package Geomstats

A Le Brigant, J Deschamps, A Collas… - ACM Transactions on …, 2023 - dl.acm.org
We introduce the information geometry module of the Python package Geomstats. The
module first implements Fisher–Rao Riemannian manifolds of widely used parametric …

Dual Model Pruning Enables Efficient Federated Learning in Intelligent Transportation Systems

J Pei, W Li - IEEE Transactions on Intelligent Transportation …, 2024 - ieeexplore.ieee.org
Federated learning significantly enhances intelligent transportation systems by enabling
collaborative model training across multiple clients, thereby improving overall performance …

Leveraging Optimal Transport via Projections on Subspaces for Machine Learning Applications

C Bonet - arXiv preprint arXiv:2311.13883, 2023 - arxiv.org
Optimal Transport has received much attention in Machine Learning as it allows to compare
probability distributions by exploiting the geometry of the underlying space. However, in its …