AI Paper Atlas

Research map / Optimization / Distributed and compressed

Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning

Milad Sefidgaran, Romain Chor, Abdellatif Zaidi

NeurIPS 2022 · Optimization › Distributed and compressed · approach: Compressed distributed optimization · 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 client-wise rate-distortion bounds that compress one local algorithm while keeping the other clients' models uncompressedDistributed learning generalization bounds · Distributed learningupper bound on generalization errorImproved
Increase the number of clientsDistributed SVM · Distributed SVMexpected generalization error: decreases with K with a rate of log(K)/KImproved
Increase the number of clientsFederated SGLD · Federated SGLDexpected generalization errorImproved
Increase the number of clientsDistributed SVM · MNIST digit 1 versus 6generalization errorImproved
Increase the number of clientsDistributed SVM · Distributed versus centralized SVMpopulation riskMixed
Increase the number of clientsDistributed SVM · Distributed SVMdifference between aggregated-model and average local empirical risksHurt

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