AI Paper Atlas

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

Certifying the True Error: Machine Learning in Coq with Verified Generalization Guarantees

Alexander Bagnall, Gordon Stewart

AAAI 2019 · Learning theory and algorithms › Kernels and regression theory · approach: Information-theoretic generalization bounds · 34 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
quantize weights to 2 bits instead of 16 bits (ablation)10-ReLU network · EMNIST Digits, union boundcertified accuracy bound: 53% -> 77%Improved
quantize weights to 2 bits instead of 16 bits (ablation)10-ReLU network · EMNIST Digitstest accuracy: 0.957 -> 0.926Hurt
quantize weights to 2 bits instead of 16 bits (ablation)10-ReLU network · EMNIST Digits, holdout boundcertified accuracy bound: 94% -> 91%Hurt
use holdout test set instead of union bound on training dataMLCert · EMNIST Digits, 2-bit netcertified accuracy bound: 77% -> 91%Improved

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