AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Relative Flatness and Generalization

Henning Petzka, Michael Kamp, Linara Adilova, Cristian Sminchisescu, Mario Boley

NeurIPS 2021 · Learning theory and algorithms › Kernels and regression theory · approach: Empirical generalization measures · 0 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 class separation (more locally constant labels) in synthetic data (ablation)relative flatness measure · Synthetic binary classificationcorrelation with generalization gapImproved
use relative flatness instead of trace of Hessian, Fisher-Rao norm, PAC-Bayes measure or weight normLeNet5 local minima · CIFAR10, 110 local minimacorrelation with generalization gapImproved
apply layer-wise reparameterization to trained networks (ablation)relative flatness and Fisher-Rao norm · CIFAR10, LeNet5correlation with generalization gapNo clear effect
apply layer-wise reparameterization to trained networks (ablation)trace of Hessian, PAC-Bayes measure, weight norm · CIFAR10, LeNet5correlation with generalization gapHurt
compute relative flatness on a fully-connected layer other than the penultimate layer (ablation)relative flatness · CIFAR10, LeNet5correlation with generalization gapMixed
add KDE-based approximation of representativeness to relative flatnessgeneralization bound · Synthetic data, 3-fold CVbound tightness on generalization gapImproved
make the learning problem easier (larger class separation)approximated generalization bound · Synthetic dataapproximated bound valueImproved

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