AI RESEARCH
Riemannian Networks over Full-Rank Correlation Matrices
arXiv CS.AI
•
ArXi:2605.19073v1 Announce Type: cross 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