AI Paper Atlas

Research map / Optimization / Optimizers

Coordinate-wise Power Method

Qi Lei, Kai Zhong, Inderjit S Dhillon

NeurIPS 2016 · Optimization › Optimizers · approach: Differentiating through embedded optimization · 32 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 CPM instead of PMpower method · soc-PokecCPU time: 118 -> 26.5Improved
Use SGCD instead of PMpower method · soc-PokecCPU time: 118 -> 5.2Improved
Use SGCD instead of PMpower method · web-StanfordCPU time: 8.15 -> 0.54Improved
Use SGCD instead of LanczosLanczos method · soc-PokecCPU time: 14.2 -> 5.2Improved
Use CPM instead of PMpower method · com-OrkutCPU time: 109.6 -> 31.5Improved
Use SGCD instead of CPMCPM · ego-GplusCPU time: 0.57 -> 0.61Hurt
Use SGCD instead of PMpower method · ego-GplusCPU time: 0.99 -> 0.61Improved
Use VRPCA instead of PMpower method · com-OrkutCPU time: 109.6 -> 189.7Hurt
Increase eigenvalue ratio lambda2/lambda1 toward 1CPM and SGCD vs PM · synthetic dense n=5000FLOPsImproved
Increase matrix dimension nCPM and SGCD · synthetic denseconvergence timeNo clear effect
Use SGCD instead of LanczosLanczos method · synthetic denseCPU timeImproved
Use PM instead of CPM/SGCD when PM converges under 0.1 secondCPM and SGCD · synthetic denseCPU timeNo 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