AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Katyusha: The First Direct Acceleration of Stochastic Gradient Methods

Zeyuan Allen-Zhu

JMLR 2018 · Optimization › Nonconvex and smooth optimization · approach: Proximal finite-sum methods · 309 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 Katyusha momentum (tau_2 = 1/2) to SVRG-style variance reduction (ablation)Katyusha · LibSVM datasets (a9a, w8a, covtype, mnist, rcv1, sensit)convergence speedImproved
use Katyusha with fixed tau_2 = 1/2 instead of tuned competitorsKatyusha · LibSVM datasetsconvergence speed vs SVRG, SAGA, Catalyst, APCGImproved
use Catalyst instead of non-accelerated variance reductionCatalyst · LibSVM datasetsconvergence speedHurt

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