AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD

PHUONG_HA NGUYEN, Lam Nguyen, Marten van Dijk

NeurIPS 2019 · Optimization › Nonconvex and smooth optimization · approach: Stochastic gradient last-iterate analysis · 16 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 the cited diminishing step-size sequences based on μ and LSGD · Strongly convex and smooth objectivesexpected squared distance Y_t: within a factor 32 of the lower boundImproved
Restrict the analysis to SGD with diminishing step sizes and derive a dimension-independent lower boundSGD on strongly convex objectives · Strongly convex objectivesexpected squared distance Y_t: 775·dImproved
Use algorithms beyond classical SGDStrongly convex optimization · Strongly convex objectivesexpected squared distance Y_t: 32·775·dMixed
Use SGD step sizes based on estimated full gradients or iterate error in addition to global parametersExtended SGD · Strongly convex and smooth objectivesexpected squared distance Y_tNo clear effect

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