Learning halfspaces with malicious noise

MaRDI QIDQ2880992zbMATH OpenFDO

Authors Adam R. Klivans, Philip M. Long, Rocco A. Servedio

Publication date 17 April 2012

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL http://www.jmlr.org/papers/v10/klivans09a.html

zbMATH Keywords

agnostic learninghalfspace learninglabel noiselinear classifiersmalicious noisenoise tolerancePAC learning

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning Halfspaces with Malicious Noise
• Learning geometric concepts with nasty noise
• Agnostically Learning Halfspaces

Cited in

(11)

• Stronger data poisoning attacks break data sanitization defenses
• Learning Halfspaces with Malicious Noise
• Robustness and generalization
• Computability of validity and satisfiability in probability logics over finite and countable models
• Resilience: a criterion for learning in the presence of arbitrary outliers
• Learning discrete distributions from untrusted batches
• scientific article; zbMATH DE number 7370646 (Why is no real title available?)
• Learning geometric concepts with nasty noise
• Efficiently learning halfspaces with Tsybakov noise
• Attribute-efficient learning of halfspaces with malicious noise: near-optimal label complexity and noise tolerance
• Understanding simultaneous train and test robustness

This page was built for publication: Learning halfspaces with malicious noise

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2880992)