technique

Riemannian classifiers

techniqueactiveprovisionalriemannian-classifiers-932cf089·1 events·first seen 15d ago

Aliases: Riemannian classifiers

Co-occurring entities

congruence-based layers SPDNet Poincaré separation theorem symmetric positive-definite matrices

More like this (12)

probing classifiers 3D Medical Image Classification neural network image classifiers Minkowski-3 Rank-Constrained Subspace Learning (RCSL)Robust Classification multimodal classification models LLM-based content classification Range Penalization: Theoretical Insights with Applications in Federated Learning Safety Detection Classifier Spherical Hellinger-Kantorovich geometry Mondrian Conformal Prediction

Recent events (1)

4arXiv · cs.LG·15d ago·source ↗

Expressivity Limits of Congruence-Based Architectures for Neural Networks on Positive-Definite Matrices

This paper analyzes neural network architectures designed to classify symmetric positive-definite (SPD) matrices, focusing on congruence-like layers as used in SPDNet. The authors prove that imposing semi-orthogonality constraints on weight matrices limits expressivity, causing deep architectures to collapse to single-hidden-layer equivalents due to spectral diversity loss—a consequence of Poincaré's separation theorem. The work also compares Riemannian classifiers for compatibility with congruence-based feature maps.

Evaluation and Benchmarking congruence-based layers SPDNet Poincaré separation theorem +2 more