AI Paper Atlas

Research map / Optimization / Distributed and compressed

Towards Optimal Communication Complexity in Distributed Non-Convex Optimization

Kumar Kshitij Patel, Lingxiao Wang, Blake Woodworth, Brian Bullins, Nathan Srebro

NeurIPS 2022 · Optimization › Distributed and compressed · approach: Communication complexity theory · 0 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 CE-LSGD with one lighter large-batch gradient instead of BVR-L-SGD's repeated heavy batchesCE-LSGD · CIFAR-10 heterogeneous, intermittent communication, M=10training loss vs communication roundsImproved
compare CE-LSGD with BVR-L-SGD at convergenceCE-LSGD · CIFAR-10 heterogeneousfinal training lossNo clear effect
compare CE-LSGD and BVR-L-SGD against FedAvg, SCAFFOLD, MB-SARAH, MB-SGD at equal updatesCE-LSGD · CIFAR-10, K=32, varying qtraining lossImproved
reduce heavy-batch size from BVR-L-SGD's to CE-LSGD'sCE-LSGD · Theory, full participationheavy-batch ratio: <= 1Improved

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