Computable PAC learning of continuous features

DOI10.1145/3531130.3533330MaRDI QIDQ6649436zbMATH OpenFDO

Authors Nathanael Ackerman, Julian Asilis, Jieqi Di, Cameron E. Freer, Jean-Baptiste Tristan

Publication date 6 December 2024

Full work available at URL https://doi.org/10.1145/3531130.3533330

zbMATH Keywords

computable analysisPAC learningVC dimension

Mathematics Subject Classification ID

Computation over the reals, computable analysis (03D78) Computational learning theory (68Q32)

Recommendations

• PAC learning, VC dimension, and the arithmetic hierarchy
• Learning by distances
• Some contributions to fixed-distribution learning theory
• On the learnability of rich function classes
• PAC learning of probability distributions over a discrete domain.

Cites work

• A theory of the learnable
• A tutorial on computable analysis
• Computability of probability measures and Martin-Löf randomness over metric spaces
• Computability on subsets of metric spaces.
• Deciding the Vapnik-Červonenkis dimension is \(\Sigma_3^p\)-complete
• scientific article; zbMATH DE number 1460545 (Why is no real title available?)
• Language identification in the limit
• Learnability and the Vapnik-Chervonenkis dimension
• Learning theory in the arithmetic hierarchy
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• PAC learning, VC dimension, and the arithmetic hierarchy
• Understanding machine learning. From theory to algorithms
• Weihrauch Complexity in Computable Analysis

This page was built for publication: Computable PAC learning of continuous features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6649436)