AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization

Xingguo Li, Tuo Zhao, Raman Arora, Han Liu, Mingyi Hong

JMLR 2018 · Optimization › Nonconvex and smooth optimization · approach: Complexity of nonconvex first-order methods · 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 block coordinate descent instead of gradient descentelastic-net and logistic regression · Elastic-net and ridge logistic, 4 covariance settingsobjective gap vs passesImproved
use cyclic instead of randomized or permuted order, ill-conditioned HessianCBCGD · Settings II and IIIobjective gap vs passesHurt
use cyclic instead of permuted order, well-conditioned HessianCBCGD · Settings I and IVobjective gap vs passesMixed
use cyclic instead of randomized orderCBCGD · Setting IVobjective gap vs passesImproved
use permuted instead of cyclic orderPBCGD · All four settingsobjective gap vs passesImproved

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