AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Asynchronous Decentralized Online Learning

Jiyan Jiang, Wenpeng Zhang, Jinjie GU, Wenwu Zhu

NeurIPS 2021 · Bandits and online learning › Online convex optimization and games · approach: Parameter-free non-stationary online learning · 5 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 asynchronous AD-OGP instead of synchronous D-OGPdecentralized online gradient-push · pokerhand, 64-node Watts-Strogatzrunning timeImproved
use asynchronous AD-OGP instead of synchronous D-OGPdecentralized online gradient-push · pokerhand, varying delay levelsaverage lossNo clear effect
add asymmetric push-sum gossiping instead of symmetric gossiping (ablation)AD-OGP · pokerhand, 64-node Watts-Strogatz, Dm=1 and 100average lossImproved
add instantaneous model averaging instead of blocked averaging (ablation)AD-OGP · pokerhand, 64-node Watts-Strogatz, Dl=1 and 100average lossImproved
increase number of learnersAD-OGP · pokerhandaverage lossHurt
use less connected network topology (ring vs complete)AD-OGP · pokerhandaverage lossHurt
increase processing delay level Dp from 1 to 100AD-OGP · pokerhandaverage lossHurt
increase message delay level Dm from 1 to 100AD-OGP · pokerhandaverage lossHurt

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