AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks

Hidenori Tanaka, Daniel Kunin

NeurIPS 2021 · Optimization › Implicit bias and generalization · approach: Edge-of-stability dynamics · 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
Allow filter norms to vary instead of constraining them to their initialization norm (ablation)VGG11 with batch normalization · Tiny ImageNet, learning rate η ∼ 0.03test accuracyImproved
Allow filter norms to vary instead of constraining them to their initialization norm (ablation)VGG11 with batch normalization · Tiny ImageNet, learning rate η ∼ 0.001test accuracyNo clear effect
Use unconstrained rather than constrained filter norms (ablation)VGG11 with batch normalization · Tiny ImageNet, large learning ratelossImproved
Add momentum (β ∼ 0.9) to amplify implicit adaptive optimizationVGG11 with batch normalization · Tiny ImageNettest accuracyImproved
Add weight decayVGG11 with batch normalization · Tiny ImageNettest 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