AI Paper Atlas

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

Generalization Bounds using Data-Dependent Fractal Dimensions

Benjamin Dupuis, George Deligiannidis, Umut Simsekli

ICML 2023 · Learning theory and algorithms › Kernels and regression theory · approach: Empirical generalization measures

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
Replace Euclidean trajectory distance with the loss-based data-dependent pseudo-metricFCN-5 · CHDSpearman's rank correlation (ρ): 0.77 -> 0.87Improved
Replace Euclidean trajectory distance with the loss-based data-dependent pseudo-metricFCN-7 · CHDSpearman's rank correlation (ρ): 0.40 -> 0.77Improved
Replace Euclidean trajectory distance with the loss-based data-dependent pseudo-metricFCN-5 · MNISTSpearman's rank correlation (ρ): 0.62 -> 0.73Improved
Replace Euclidean trajectory distance with the loss-based data-dependent pseudo-metricFCN-7 · MNISTSpearman's rank correlation (ρ): 0.80 -> 0.89Improved
Replace Euclidean trajectory distance with the loss-based data-dependent pseudo-metricAlexNet · CIFAR-10Spearman's rank correlation (ρ): 0.86 -> 0.93Improved
Estimate the data-dependent pseudo-metric from a random subset rather than the full training setPH dimension computation · MNIST and CHDRelative error in PH dimension: 40%No clear effect

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