AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement

Yoonsoo Nam, Nayara Fonseca, Seok Hyeong Lee, Chris Mingard, Niclas Alexander Göring, Ouns El Harzli, Abdurrahman Hadi Erturk, Soufiane Hayou, Ard A. Louis

ICLR 2026 · Architectures and efficiency › RNNs and normalization · approach: Symmetry and equivariance in loss landscapes · 4 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 batch normalization to VGG-16 (ablation)VGG-16 · CIFAR-100test accuracy: 21.7% -> 72.0%Improved
add batch normalization to VGG-16 (ablation)VGG-16 · CIFAR-100D_LR: 0.66 -> 0.073Improved
increase weight decay from 0 to 1e-3 (ablation)ResNet18 · CIFAR-10test accuracy: 93.5% -> 94.8%Improved
increase weight decay from 0 to 1e-3 (ablation)ResNet18 · CIFAR-10D_LR: 0.05 -> 0.003Improved
raise learning rate from 0.005 to 0.05 (ablation)ResNet18 · CIFAR-100test accuracy: 66.3% -> 78.3%Improved
raise learning rate from 0.05 to 0.2 (ablation)ResNet18 · CIFAR-100test accuracy: 78.3% -> 74.5%Hurt
use ResNet18 instead of MLP (ablation)ResNet18 · CIFAR-10test accuracy: 55.4% -> 94.8%Improved
train the full network instead of last layer only (ablation)CNN · MNISTD_LR: 0.51 -> 0.043Improved
shuffle 10% of labels (ablation)ResNet18 · CIFAR-10test accuracy: 95.0% -> 66.1%Hurt
shuffle labels fully (ablation)ResNet18 · CIFAR-10D_LR: 0.031 -> 0.034No clear effect
train through grokking from step 200 to step 30002-layer transformer · Mod 97D_LR: 0.51 -> 0.11Improved
increase target downscaling alpha from 0.2 to 20 (ablation)MLP · CIFAR-10test accuracy: 92.7% -> 88.3%Hurt

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