AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay

Zhiyuan Li, Tianhao Wang, Dingli Yu

NeurIPS 2022 · Optimization › Implicit bias and generalization · approach: SGD noise and flat minima · 1 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 weight decay to SGD on a scale-invariant lossSGD on scale-invariant loss · limiting diffusion mixing time (theory, Theorem 3.2)time scale to reach limiting diffusionImproved
use the rescaled time scale ln(1+(e^{4 eta lambda t}-1) eta/(2 lambda))/2 instead of plain T/(eta lambda)SGD+WD on normalized linear model · Synthetic normalized linear regression, D=10, lambda=0.05fit of dynamics to predicted time scaleImproved
train longer with SGD+WD after parameter norm has converged, then decay LR32-layer PreResNet · CIFAR-10test accuracy after LR decayImproved
train longer once train accuracy and parameter norm have plateaued32-layer PreResNet · CIFAR-10train accuracyNo 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