AI Paper Atlas

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

Chaining Mutual Information and Tightening Generalization Bounds

Amir Asadi, Emmanuel Abbe, Sergio Verdu

NeurIPS 2018 · Learning theory and algorithms › Kernels and regression theory · approach: Information-theoretic generalization bounds · 13 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 chained mutual information instead of classical chainingUpper-bounding E[X_W] for the canonical Gaussian process · Canonical Gaussian process, ε=1/20upper bound on E[X_W]: 19.0352 -> 1.1013Improved
Use chained mutual information instead of the mutual information boundUpper-bounding E[X_W] for the canonical Gaussian process with degenerate noise · Canonical Gaussian process, ε=1/20upper bound on E[X_W]: ∞ -> 1.1013Improved
Decrease the probability mass ε on zero in the output noiseChained mutual information bound · Canonical Gaussian process, ε=1/20 to ε=1/400upper bound on E[X_W]: 1.1013 -> 0.0610Improved

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