AI Paper Atlas

Research map / Optimization / Distributed and compressed

Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning

Tomoya Murata, Taiji Suzuki

NeurIPS 2022 · Optimization › Distributed and compressed · approach: Decentralized optimization algorithms · 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
Add parameter perturbation (BVR-L-PSGD) to BVR-L-SGDBVR-L-SGD · heterogeneous CIFAR10 (q=0.35), 3-layer MLPtrain lossImproved
Add parameter perturbation (BVR-L-PSGD) to BVR-L-SGDBVR-L-SGD · heterogeneous CIFAR10 (q=0.35), 3-layer MLPtest accuracyImproved
Add perturbation to escape small-gradient-norm regionBVR-L-SGD · heterogeneous CIFAR10 (q=0.35), 3-layer MLPescape time of stuck regionImproved
Use BVR-L-PSGD instead of Minibatch SGDdistributed training · heterogeneous CIFAR10 (q=0.35), 3-layer MLPtest accuracy / train lossImproved
Use BVR-L-PSGD instead of Noisy Minibatch SGDdistributed training · heterogeneous CIFAR10 (q=0.35), 3-layer MLPtest accuracy / train lossImproved
Add perturbation on top of BVR-L-SGD (theory)BVR-L-SGD · nonconvex distributed optimizationcommunication roundsNo 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