Enregistré dans:
Détails bibliographiques
Auteurs principaux: Oswald, Antonin, Massart, Estelle
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2606.02490
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910282360553472
author Oswald, Antonin
Massart, Estelle
author_facet Oswald, Antonin
Massart, Estelle
contents This work studies neural architectures for classifying symmetric positive-definite matrices, focusing on congruence-like layers, in which the input matrix is multiplied on the left and right by a (possibly rectangular) weight matrix $W$ and its transpose. Such layers lie at the core of the celebrated SPDNet and have also been employed independently for dimensionality reduction on positive-definite data. We show that the (semi)-orthogonality constraint commonly imposed on $W$ limits the expressivity of these layers: for certain activation functions, the resulting architecture collapses to a one-hidden-layer equivalent. This lack of expressivity follows from a loss of spectral diversity in congruence-like layers for semi-orthogonal $W$ and is a direct consequence of Poincaré's separation theorem. We then examine the choice of the final classifier, comparing several Riemannian classifiers and discussing their compatibility with the feature maps produced by congruence-like layers.
format Preprint
id arxiv_https___arxiv_org_abs_2606_02490
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Expressivity of congruence-based architectures for DNNs on positive-definite matrices
Oswald, Antonin
Massart, Estelle
Machine Learning
This work studies neural architectures for classifying symmetric positive-definite matrices, focusing on congruence-like layers, in which the input matrix is multiplied on the left and right by a (possibly rectangular) weight matrix $W$ and its transpose. Such layers lie at the core of the celebrated SPDNet and have also been employed independently for dimensionality reduction on positive-definite data. We show that the (semi)-orthogonality constraint commonly imposed on $W$ limits the expressivity of these layers: for certain activation functions, the resulting architecture collapses to a one-hidden-layer equivalent. This lack of expressivity follows from a loss of spectral diversity in congruence-like layers for semi-orthogonal $W$ and is a direct consequence of Poincaré's separation theorem. We then examine the choice of the final classifier, comparing several Riemannian classifiers and discussing their compatibility with the feature maps produced by congruence-like layers.
title Expressivity of congruence-based architectures for DNNs on positive-definite matrices
topic Machine Learning
url https://arxiv.org/abs/2606.02490