AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

LieGG: Studying Learned Lie Group Generators

Artem Moskalev, Anna Sepliarskaia, Ivan Sosnovik, Arnold W.M. Smeulders

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Symmetry and equivariance in loss landscapes · 6 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
increase training set size (ablation)MLP · O(5) synthetic regressionsymmetry varianceImproved
increase number of parameters (ablation)MLP · rotation-MNISTsymmetry varianceImproved
deeper instead of wider network at same parameter count (ablation)MLP · rotation-MNISTsymmetry varianceImproved
increase depth beyond 3 layers (ablation)MLP · rotation-MNISTsymmetry biasMixed
use deeper 6-layer network instead of shallow 2-layer (ablation)MLP · rotation-MNISTsymmetry biasImproved
pre-train sub-network then fine-tune or layer-wise train (ablation)MLP-7 · rotation-MNISTintermediate layer symmetry bias and varianceImproved
vary training regime (end-to-end, fine-tune, layer-wise) (ablation)MLP-7 · rotation-MNISTfinal-layer symmetryNo clear effect
lower symmetry variance and bias vs accuracyMLP · rotation-MNISTclassification accuracy: -0.49Mixed

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