On the complexity of proper distribution-free learning of linear classifiers

MaRDI QIDQ7025123zbMATH OpenFDO

Authors Philip M. Long, Raphael J. Long

Publication date 19 February 2025

Full work available at URL https://proceedings.mlr.press/v117/long20a.html

zbMATH Keywords

linear classifierslower boundsstatistical learning theory

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A general lower bound on the number of examples needed for learning
• scientific article; zbMATH DE number 3128740 (Why is no real title available?)
• Learning faster than promised by the Vapnik-Chervonenkis dimension
• Predicting \(\{ 0,1\}\)-functions on randomly drawn points
• Strong minimax lower bounds for learning
• The one-inclusion graph algorithm is near-optimal for the prediction model of learning
• The sample complexity of learning linear predictors with the squared loss
• Zur Theorie der Gesellschaftsspiele.

This page was built for publication: On the complexity of proper distribution-free learning of linear classifiers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7025123)