AI Paper Atlas

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

Harmonic Mean Iteratively Reweighted Least Squares for Low-Rank Matrix Recovery

Christian Kümmerle, Juliane Sigl

JMLR 2018 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory · 17 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 harmonic mean weights (HM-IRLS) instead of arithmetic mean or column weightsIRLS for low-rank recovery · Matrix completion 100x100 rank-8 (150 instances)empirical recovery probability: almost 100% at rho = 1.5 -> 100% from rho = 1.2Improved
use HM-IRLS instead of non-IRLS algorithmslow-rank recovery · Matrix completion 100x100 rank-8 (150 instances)empirical recovery probability: 100% from rho = 1.2 vs never recover for rho < 1.2Improved
use small non-convex p (<= 0.25) in HM-IRLS (ablation)HM-IRLS · Matrix completion rho=1.0relative Frobenius error: p <= 0.25Improved
use p=0.8 instead of small p (ablation)HM-IRLS · Matrix completion rho=1.2relative Frobenius error: 0.27 after 100 iterationsHurt
use IRLS-MF smoothing instead of IRLS-col smoothingIRLS · Matrix completion 100x100 rank-8 (150 instances)empirical recovery probabilityHurt

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