AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Divide-and-Conquer Learning with Nyström: Optimal Rate and Algorithm

Rong Yin, Yong Liu, Lijing Lu, Weiping Wang, Dan Meng

AAAI 2020 · Learning theory and algorithms › Kernels and regression theory · approach: RKHS kernel methods · 9 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
add divide-and-conquer (p=2) to Nystrom-iterativeNY · covtype, m=2000training time (s): 5.62 -> 2.63Improved
add divide-and-conquer (p=2) to Nystrom-iterativeNY · SUSY, m=2000training time (s): 12.9 -> 6.40Improved
add divide-and-conquer (p=2) to Nystrom-iterativeNY · SUSY, m=2000test error: 0.195 -> 0.195No clear effect
add divide-and-conquer (p=2) to Nystrom-iterativeNY · HIGGS, m=2000test error: 0.321 -> 0.322No clear effect
use Nystrom instead of random features in divide-and-conquer (ablation)DC-RF · covtype, m=2000test error: 0.234 -> 0.185Improved
use Nystrom instead of random features in divide-and-conquer (ablation)DC-RF · SUSY, m=2000training time (s): 13.67 -> 6.40Improved
increase number of partitions pDC-NY · four datasetstest errorHurt
increase number of partitions pDC-RF and DC-NY · four datasetstraining timeImproved
increase conjugate gradient iterations t beyond 4 (ablation)DC-NY · four datasetstest errorNo clear effect
increase sampling scale m up to sqrt(N) (ablation)DC-NY · four datasetstest errorImproved
increase sampling scale m (ablation)DC-NY · four datasetstraining timeHurt

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