AI Paper Atlas

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

Low-rank Tensor Estimation via Riemannian Gauss-Newton: Statistical Optimality and Second-Order Convergence

Yuetian Luo, Anru R. Zhang

JMLR 2023 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory · 16 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 RGN instead of PGDprojected gradient descent · MRI image recovery (100 images)runtime (seconds): 79.5 -> 39.2Improved
Use RGN instead of RTRRiemannian trust region · MRI image recovery (100 images)runtime (seconds): 104.9 -> 39.2Improved
Use RGN instead of PGDprojected gradient descent · MRI image recovery (100 images)relative RMSE: 0.300 -> 0.155Improved
Use RGN instead of RTRRiemannian trust region · MRI image recovery (100 images)relative RMSE: 0.153 -> 0.155No clear effect
Use RGN instead of RTRRiemannian trust region · noiseless tensor regression (p=30, r=3)convergence speedImproved
Use RGN instead of GD, PGD, Alter Minifirst-order and alternating baselines · noiseless and noisy tensor regression (p=30, r=3)convergence rate and runtimeImproved
Use random initialization instead of spectral initializationRGN · tensor regression and rank-1 projectionssample size needed / stabilityHurt
Use RGN initialized with T-HOSVDRGN · tensor SVDiterations to convergeImproved

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