AI Paper Atlas

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

Affine Rank Minimization via Asymptotic Log-Det Iteratively Reweighted Least Squares

Sebastian Krämer

JMLR 2025 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory

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
lower weight strength p from 1 to 0 (log-det limit) (ablation)IRLS-p · Matrix recovery, Gaussian, l=63recovery rate (%): 0.0 -> 31.9Improved
lower weight strength p from 1 to 0 (ablation)IRLS-p · Matrix recovery, Gaussian, l=72recovery rate (%): 0.0 -> 99.0Improved
lower weight strength p from 0.8 to 0 (ablation)IRLS-p · Matrix recovery, Gaussian, l=72recovery rate (%): 49.8 -> 99.0Improved
lower weight strength p from 1.0 to 0 (ablation)IRLS-p · Matrix recovery, Gaussian, l=108recovery rate (%): 98.8 -> 100.0No clear effect
use both-sided weights instead of one-sided (ablation)IRLS-0 · Matrix recovery, Gaussian, l=63, kmax=14recovery rate (%): 34.0 -> 43.2Improved
use both-sided weights instead of one-sided (ablation)IRLS-0 · Matrix recovery, sampling, l=64, kmax=14recovery rate (%): 22.9 -> 35.9Improved
use both-sided weights instead of one-sided (ablation)IRLS-0 · Matrix recovery, sampling, l=63, kmax=12recovery rate (%): 5.6 -> 24.0Improved
increase measurements from 62 to 64IRLS-0 gaussian · Matrix recovery, kmax=14recovery rate (%): 0.0 -> 58.2Improved
increase measurements from 63 to 72IRLS-0 gaussian · Matrix recovery, kmax=12recovery rate (%): 31.9 -> 99.0Improved
use Gaussian measurements instead of samplingIRLS-0 · Matrix recovery, l=72, kmax=12recovery rate (%): 77.1 -> 99.0Improved
increase measurements from 72 to 108 for samplingIRLS-0 sampling · Matrix recovery, kmax=12recovery rate (%): 77.1 -> 100.0Improved

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