AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry

Ziheng Chen, Yue Song, Xiaojun Wu, Nicu Sebe

ICLR 2026 · Learning theory and algorithms › Matrix and tensor methods · approach: Geometry of low-rank and SPD structure · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use CDEM instead of LCM in SPD MLRSPDNet · FPHAaccuracy: 86.37 -> 89.40Improved
use CDBWM instead of LCM in SPD MLRSPDNet · HDM05 3-blockaccuracy: 62.33 -> 67.40Improved
use CDBWM instead of AIM in SPD MLRSPDNet · Radaraccuracy: 94.53 -> 93.93Hurt
use CDEM instead of LCM in SPD MLRGyroSPD · HDM05accuracy: 68.37 -> 71.93Improved
use CDBWM instead of AIM in SPD MLRGyroSPD · Radaraccuracy: 96.80 -> 96.21Hurt
use CDEM instead of LCM in residual blockRResNet · HDM05accuracy: 66.27 -> 68.05Improved
tune Cholesky power deformation theta (-0.5) instead of theta=1 (ablation)CDEM on SPDNet · HDM05 3-blockaccuracy: 64.58 -> 65.75Improved
tune Cholesky power deformation theta (-1.5) instead of theta=1 (ablation)CDBWM on SPDNet · HDM05 3-blockaccuracy: 63.33 -> 67.40Improved
tune Cholesky power deformation theta (-0.75) instead of theta=1 (ablation)CDEM on GyroSPD · HDM05accuracy: 67.80 -> 71.93Improved
set extreme theta=-2 in CDEM (ablation)CDEM on SPDNet · HDM05 3-blockaccuracy: 64.58 -> 46.63Hurt
tune theta (-1.5) instead of theta=1 (ablation)CDEM on SPDNet · Radaraccuracy: 93.87 -> 95.79Improved
use diagonal power deformation (DPM, theta=0.15) instead of diagonal log (DLM) (ablation)geodesic computation · 3x3 Cholesky, eps=1e-3failure probability (%): 51.32 -> 0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy