Dimension-adaptive bounds on compressive FLD classification

DOI10.1007/978-3-642-40935-6_21MaRDI QIDQ2859225zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Ata Kabán, Robert J. Durrant

Publication date 6 November 2013

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://hdl.handle.net/10289/8939

zbMATH Keywords

random projectionsintrinsic dimensioncompressed learning

Mathematics Subject Classification ID

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

Recommendations

• Random projections as regularizers: learning a linear discriminant from fewer observations than dimensions
• Convergence rates of learning algorithms by random projection
• Structure from randomness in halfspace learning with the zero-one loss
• Random projections of smooth manifolds
• Stability of random-projection based classifiers. The Bayes error perspective

Cited in

(6)

• Random projections as regularizers: learning a linear discriminant from fewer observations than dimensions
• The effect of intrinsic dimension on the Bayes-error of projected quadratic discriminant classification
• Tighter guarantees for the compressive multi-layer perceptron
• Stability of random-projection based classifiers. The Bayes error perspective
• Structure from randomness in halfspace learning with the zero-one loss
• Compressive classification: where wireless communications meets machine learning

This page was built for publication: Dimension-adaptive bounds on compressive FLD classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2859225)