AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning

Charles H. Martin, Michael W. Mahoney

JMLR 2021 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse

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
train MLP3 with backprop (versus random initialization)MLP3 FC2 · CIFAR10matrix entropy: 0.92 -> just below 0.91Improved
train MLP3 with backprop (versus random initialization)MLP3 FC2 · CIFAR10stable rank: decreases by approximately a factor of twoImproved
training MLP3 FC2: spectral norm squaredMLP3 FC2 · CIFAR10squared spectral norm: lambda_max 3.2 -> 7.2Improved
older small model (LeNet5) versus large modern models (AlexNet) ESD fit to MPESD analysis · Pretrained DNN layersfit to Marchenko-Pastur: LeNet5 lambda+ ~ 3.5 well fit; AlexNet alpha 2.25-3.02 heavy-tailedHurt

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