AI Paper Atlas

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

A Fast Scale-Invariant Algorithm for Non-negative Least Squares with Non-negative Data

Jelena Diakonikolas, Chenghui Li, Swati Padmanabhan, Chaobing Song

NeurIPS 2022 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory · 1 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 SI-NNLS+ instead of FISTA and OA+DSNNLS · real-simnumber of data passesImproved
Add adaptive restart to SI-NNLS+SI-NNLS+ · real-simconvergence to high accuracyImproved
Use block size 1 instead of 10SI-NNLS+ with restart · real-simconvergenceImproved
Use SI-NNLS+ with restart bs=1 instead of FISTA/OA+DSNNLS · real-simruntimeImproved
Use SI-NNLS+ instead of FISTA and OA+DSNNLS · news20number of data passesImproved
Use block size 1 instead of 10SI-NNLS+ · news20runtimeHurt
Use block size 10 with SI-NNLS+SI-NNLS+ · news20runtimeImproved
Use SI-NNLS+ instead of FISTA and OA+DSNNLS · E2006trainfunction value reductionImproved

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