activity
20242026
most citedUnderstanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry

1 citations · 1 across the 15 of their papers we have counts for

collaborators
Showing 2025Show all

2 papers · 1 filter

cs.LG2025

Riemannian Batch Normalization: A Gyro Approach

Ziheng Chen, Xiao-Jun Wu, Bernhard Schölkopf +1

Normalization layers are crucial for deep learning, but their Euclidean formulations are inadequate for data on manifolds. On the other hand, many Riemannian manifolds in machine l…

cs.LG2025

Learning to Normalize on the SPD Manifold under Bures-Wasserstein Geometry

Rui Wang, Shaocheng Jin, Ziheng Chen +2

Covariance matrices have proven highly effective across many scientific fields. Since these matrices lie within the Symmetric Positive Definite (SPD) manifold - a Riemannian space…