Riemannian Networks over Full-Rank Correlation Matrices

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Ziheng, Wu, Xiaojun, Schölkopf, Bernhard, Sebe, Nicu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911696532013056
author Chen, Ziheng
Wu, Xiaojun
Schölkopf, Bernhard
Sebe, Nicu
author_facet Chen, Ziheng
Wu, Xiaojun
Schölkopf, Bernhard
Sebe, Nicu
contents Representations on the Symmetric Positive Definite (SPD) manifold have garnered significant attention across different applications. In contrast, the manifold of full-rank correlation matrices, a normalized alternative to SPD matrices, remains largely underexplored. This paper introduces Riemannian networks over the correlation manifold, leveraging five recently developed correlation geometries. We systematically extend basic layers, including Multinomial Logistic Regression (MLR), Fully Connected (FC), and convolutional layers, to these geometries. Besides, we present methods for accurate backpropagation for two correlation geometries. Experiments comparing our approach against existing SPD and Grassmannian networks demonstrate its effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19073
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Riemannian Networks over Full-Rank Correlation Matrices
Chen, Ziheng
Wu, Xiaojun
Schölkopf, Bernhard
Sebe, Nicu
Machine Learning
Artificial Intelligence
Representations on the Symmetric Positive Definite (SPD) manifold have garnered significant attention across different applications. In contrast, the manifold of full-rank correlation matrices, a normalized alternative to SPD matrices, remains largely underexplored. This paper introduces Riemannian networks over the correlation manifold, leveraging five recently developed correlation geometries. We systematically extend basic layers, including Multinomial Logistic Regression (MLR), Fully Connected (FC), and convolutional layers, to these geometries. Besides, we present methods for accurate backpropagation for two correlation geometries. Experiments comparing our approach against existing SPD and Grassmannian networks demonstrate its effectiveness.
title Riemannian Networks over Full-Rank Correlation Matrices
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.19073