Nearly optimal classification for semimetrics

MaRDI QIDQ5361299zbMATH OpenFDO

Authors Pinhas Nisnevitch, Lee-Ad Gottlieb, Aryeh Kontorovich

Publication date 27 September 2017

Full work available at URL http://jmlr.csail.mit.edu/papers/v18/16-217.html

zbMATH Keywords

classificationcompressiongeneralizationsemimetric

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Statistics on metric spaces (62R20) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17)

Recommendations

• Learning bounds via sample width for classifiers on finite metric spaces
• Using the doubling dimension to analyze the generalization of learning algorithms
• Large-width bounds for learning half-spaces on distance spaces
• Distance-based classification with Lipschitz functions
• Distance-based classification with Lipschitz functions.

Cited in

(7)

• Large-width bounds for learning half-spaces on distance spaces
• Universal Bayes consistency in metric spaces
• Non-uniform packings
• Learning half-spaces on general infinite spaces equipped with a distance function
• scientific article; zbMATH DE number 4066166 (Why is no real title available?)
• Active nearest-neighbor learning in metric spaces
• On the strong consistency of feature-weighted \(k\)-means clustering in a nearmetric space

This page was built for publication: Nearly optimal classification for semimetrics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5361299)