AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Breaking the Span Assumption Yields Fast Finite-Sum Minimization

Robert Hannah, Yanli Liu, Daniel O'Connor, Wotao Yin

NeurIPS 2018 · Optimization › Nonconvex and smooth optimization · approach: Proximal finite-sum methods · 6 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 SVRG instead of SAGAfinite-sum minimizer · least squares kappa=5decibels/epoch: 2.1 -> 6.3Improved
use SARAH instead of SAGAfinite-sum minimizer · least squares kappa=5decibels/epoch: 2.1 -> 4.9Improved
use SVRG instead of SAGAfinite-sum minimizer · least squares kappa=10decibels/epoch: 2.3 -> 6.2Improved
use SARAH instead of SAGAfinite-sum minimizer · least squares kappa=10decibels/epoch: 2.3 -> 5.0Improved
use SVRG instead of SAGAfinite-sum minimizer · least squares kappa=20decibels/epoch: 2.1 -> 6.0Improved
use SARAH instead of SAGAfinite-sum minimizer · least squares kappa=20decibels/epoch: 2.1 -> 4.3Improved
early iterations: SAGA versus SVRG and SARAHSAGA · least squaresinitial convergenceMixed

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