AI Paper Atlas

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

On Leave-One-Out Conditional Mutual Information For Generalization

Mohamad Rida Rammal, Alessandro Achille, Aditya Golatkar, Suhas Diggavi, Stefano Soatto

NeurIPS 2022 · Learning theory and algorithms › Kernels and regression theory · approach: Information-theoretic generalization bounds · 1 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
Use f-CMI (prediction-based) bound instead of loo-CMI (weight-based) bound (ablation)CMI generalization bound · MIT-67generalization bound: 9.65 -> 0.493Improved
Use f-CMI bound instead of loo-CMI bound (ablation)CMI generalization bound · Oxford Petsgeneralization bound: 8.51 -> 0.514Improved
Increase training set size (fraction of dataset)f-CMI bound · MIT-67 and Oxford Petsgeneralization boundImproved
Increase noise std sigmaf-CMI bound · image classificationgeneralization boundImproved
Increase noise std sigmanoised model h_sigma · image classificationtest errorHurt

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