atlas

Research map / Optimization / Nonconvex and smooth optimization

Limitations on Variance-Reduction and Acceleration Schemes for Finite Sums Optimization

NeurIPS 2017 · Optimization › Nonconvex and smooth optimization · approach: Proximal finite-sum methods · 6 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Hide the identity of the sampled individual functionFinite sum optimization with a stochastic oracle · Smooth and strongly convex finite sumsoracle calls: n^2/2Hurt
Require the strong convexity parameter to be unknown to the algorithmOblivious finite sum algorithms with first-order and coordinate-descent oracles · Smooth and strongly convex finite sumsiteration complexity: tildeOmega(n+ kappa ln(1/epsilon))Hurt
Restrict the algorithm to stationary update rulesOblivious finite sum algorithms with first-order and coordinate-descent oracles · Smooth and convex finite sumsiteration complexity: Omega(n+L/epsilon)Hurt
Use an oblivious algorithm without restricting it to stationary updatesFinite sum algorithms with first-order and coordinate-descent oracles · Smooth and convex finite sumsiteration complexity: Omega(n+sqrt(nL/epsilon))Hurt

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