AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Why neural networks find simple solutions: The many regularizers of geometric complexity

Benoit Dherin, Michael Munn, Mihaela Rosca, David GT Barrett

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 10 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 L2, spectral or flatness regularization strengthResNet18/MLP · CIFAR10/MNISTgeometric complexityImproved
increase label noise proportionResNet18, MLP · CIFAR10, MNISTgeometric complexityImproved
use larger learning rateResNet18 · CIFAR10geometric complexity (lower) and test accuracyImproved
use smaller batch sizeResNet18 · CIFAR10geometric complexity (lower) and test accuracyImproved
add explicit GC (Jacobian) regularizationMLP, ResNet18 · MNIST, CIFAR10test accuracyImproved
increase network depth at initializationReLU MLP · initializationgeometric complexityImproved

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