Structure from randomness in halfspace learning with the zero-one loss

DOI10.1613/JAIR.1.11506MaRDI QIDQ5139592zbMATH OpenOpenAlexFDO

Authors Ata Kabán, Robert J. Durrant

Publication date 9 December 2020

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1613/jair.1.11506

zbMATH Keywords

knowledge discoverymachine learningmathematical foundationsphilosophical foundations

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Convergence rates of learning algorithms by random projection
• Compressed learning with regular concept
• Learning Theory
• Learning intersections of halfspaces with a margin
• Dimension-adaptive bounds on compressive FLD classification

Cites work

• 10.1162/153244303321897690
• A simple tool for bounding the deviation of random matrices on geometric sets
• An algorithmic theory of learning: Robust concepts and random projection
• An elementary proof of a theorem of Johnson and Lindenstrauss
• Boosting the margin: a new explanation for the effectiveness of voting methods
• Bounds on the Number of Measurements for Reliable Compressive Classification
• Compressed sensing
• Database-friendly random projections: Johnson-Lindenstrauss with binary coins.
• Empirical margin distributions and bounding the generalization error of combined classifiers
• Empirical processes and random projections
• Explaining AdaBoost
• Extensions of Lipschitz mappings into a Hilbert space
• Foundations of machine learning
• High-dimensional probability. An introduction with applications in data science
• scientific article; zbMATH DE number 1333813 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 1149836 (Why is no real title available?)
• scientific article; zbMATH DE number 3273551 (Why is no real title available?)
• Kernels as features: on kernels, margins, and low-dimensional mappings
• Living on the edge: phase transitions in convex programs with random data
• On the doubt about margin explanation of boosting
• On variants of the Johnson–Lindenstrauss lemma
• Robust 1-bit Compressed Sensing and Sparse Logistic Regression: A Convex Programming Approach
• Theory of Classification: a Survey of Some Recent Advances

Cited in

(5)

• Convergence rates of learning algorithms by random projection
• Dimension-adaptive bounds on compressive FLD classification
• Compressed learning with regular concept
• Tighter guarantees for the compressive multi-layer perceptron
• Efficiently learning halfspaces with Tsybakov noise

Describes a project that uses

Uses Software

• UCI

This page was built for publication: Structure from randomness in halfspace learning with the zero-one loss

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5139592)