AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training

Diego Granziol, Stefan Zohren, Stephen Roberts

JMLR 2022 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 42 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
scale initial learning rate linearly with batch size (alpha_0 = 0.01B/128)VGG-16 SGD without BN or weight decay · CIFAR-100validation accuracy: small drop at B=1024, larger drop at B=2048, no training at B=4096Mixed
double the maximal allowed learning rate (ablation)VGG-16 SGD · CIFAR-100training stabilityHurt
use a mini-batch Hessian (B=128) instead of the full Hessian (ablation)VGG-16 Hessian spectrum · CIFAR-100extremal eigenvalue magnitudeHurt
use multiplicative noise model instead of additive noise for predicting batch eigenvalues (ablation)Perturbation theory prediction · VGG-16 CIFAR-100fit to batch Hessian max eigenvalueImproved
use larger initial learning rate at fixed B=1024 (ablation)VGG-16 SGD · CIFAR-100validation/test accuracyImproved

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