AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Traditional and Heavy Tailed Self Regularization in Neural Network Models

Michael Mahoney, Charles Martin

ICML 2019 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 38 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
decrease batch size from 500 to 2 (ablation)MiniAlexNet · CIFAR10test accuracyMixed
decrease batch size (ablation)MiniAlexNet · CIFAR10MP Soft RankImproved
decrease batch size (ablation)MiniAlexNet · CIFAR10Stable RankImproved
decrease batch size (ablation)MiniAlexNet · CIFAR10training accuracyMixed
add explicit regularization, such as L2 weight regularization or Dropout (ablation)MiniAlexNet · CIFAR10complexity metrics (entropy and Stable Rank)Improved
train the modelMiniAlexNet · CIFAR10largest eigenvalue λmax: roughly 3.0 to roughly 4.0Mixed

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