AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Decentralized Nonconvex Optimization under Heavy-Tailed Noise: Normalization and Optimal Convergence

Shuhua Yu, Dusan Jakovetic, Soummya Kar

ICLR 2026 · Optimization › Nonconvex and smooth optimization · approach: Stochastic gradient last-iterate analysis · 4 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 GT-NSGDm instead of DSGD-Clipdecentralized training · Multi30k GPT, ringvalidation loss: 5.633 -> 0.258Improved
use GT-NSGDm instead of SClip-EF-Networkdecentralized training · Multi30k GPT, ringvalidation loss: 5.653 -> 0.258Improved
use GT-NSGDm instead of DSGD-GClip (no theory)decentralized training · Multi30k GPT, ringvalidation loss: 0.253 -> 0.258No clear effect
use GT-NSGDm instead of GT-Adamdecentralized training · Multi30k GPT, complete graphvalidation loss: 0.524 -> 0.282Improved
weaker connectivity (ring vs complete graph) (ablation)GT-NSGDm · synthetic regression, Levy noisefinal errorNo clear effect
add gradient tracking and normalization instead of plain DSGDdecentralized SGD · synthetic regression, heavy-tailed noiseestimation errorImproved

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