AI Paper Atlas

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

Accelerating Nuclear-norm Regularized Low-rank Matrix Optimization Through Burer-Monteiro Decomposition

Ching-pei Lee, Ling Liang, Tianyun Tang, Kim-Chuan Toh

JMLR 2024 · Learning theory and algorithms › Matrix and tensor methods · approach: Matrix completion and factorization · 7 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 BM-Global instead of QSDPNALconvex QSDP solving · Regularized kernel estimation, polydism57running time (s): 3286.4 -> 305.0Improved
use BM-Global instead of QSDPNALconvex QSDP solving · Regularized kernel estimation, polydish57running time (s): 3508.9 -> 1765.2Improved
use BM-Global instead of QSDPNALconvex QSDP solving · Regularized kernel estimation, WoodyPlants50running time (s): 44.3 -> 78.2Hurt
use BM-Global instead of QSDPNALconvex QSDP solving · Regularized kernel estimation, delftgesturesrunning time (s): 318.3 -> 390.1Hurt
use BM-Global instead of QSDPNALconvex QSDP solving · Regularized kernel estimation, zongkeroptimality eta_opt: 1e-02 -> 1e-04Improved
use BM-Global instead of QSDPNALconvex QSDP solving · Molecular conformation, 1LFBrunning time (s): 2739.5 -> 25.5Improved
use BM-Global instead of QSDPNALconvex QSDP solving · Molecular conformation, 1LFBRMSD: 1.2 -> 1.5Hurt
use BM-Global instead of QSDPNALconvex QSDP solving · Molecular conformation, 1F39RMSD: 1.3 -> 0.8Improved
alternate x=1 inexact proximal gradient step with y=3 BM iterations (ablation)BM-Global · Matrix completion toy example and movielens100kobjective convergenceNo clear effect
use BM-Global instead of BM solver alone (polyMF-SS)matrix factorization · Matrix completion, 4 data setsrelative objectiveImproved
use BM-Global instead of Active-ALT and AIS-Imputematrix completion · movielens, netflix, yahoo-musictime to relative RMSEImproved
use fixed step size 1.99 instead of SpaRSA spectral step with linesearch (ablation)BM-Global · Matrix completionperformanceNo clear effect

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