AI Paper Atlas

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

A Unified Framework for Structured Low-rank Matrix Learning

Pratik Jawanpuria, Bamdev Mishra

ICML 2018 · Learning theory and algorithms › Matrix and tensor methods · approach: Matrix completion and factorization · 6 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 RSLM second-order (trust region) solver instead of first-order CGRSLM · Netflix / ML10m / ML20m matrix completiontest RMSE: 0.8449 -> 0.8443No clear effect
Use RSLM-tr instead of R3MCfixed-rank matrix completion · Netflixtest RMSE: 0.8478 -> 0.8443Improved
Use RSLM-tr instead of nuclear-norm APGLmatrix completion · ML20mtest RMSE: 0.8160 -> 0.7962Improved
Use RSLM with epsilon-SVR loss instead of l1 lossrobust matrix completion · Netflixtest RMSE: 0.869 -> 0.857Improved
Replace RMC pseudo-Huber loss with RSLM l1 lossrobust matrix completion · Netflixtest RMSE: 0.868 -> 0.869No clear effect
Use RSLM instead of BMCnon-negative matrix completion, rank 20 · ML20mtest RMSE: 0.9130 -> 0.8065Improved
Use RSLM instead of BMCnon-negative matrix completion, rank 10 · ML1mtest RMSE: 0.8529 -> 0.8574Hurt
Use RSLM instead of BMC on larger data setsnon-negative matrix completion · ML10m / ML20mtest RMSE: 0.8454 -> 0.8142Improved
Use RSLM instead of BMC for convergence of primal objectivenon-negative matrix completion · ML10m, ML20mobjective value vs timeImproved
Use RSLM instead of SLRAHankel matrix learning · D2, rank 5RMSE: 0.0164 -> 0.0059Improved
Use RSLM instead of SLRAHankel matrix learning · D3, rank 5RMSE: 0.0149 -> 0.0149No clear effect
Set rank equal to true system order r0RSLM · Hankel D1-D3RMSEImproved

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