Short proofs for online multiclass prediction on graphs

DOI10.1016/J.IPL.2010.02.008MaRDI QIDQ991792zbMATH OpenOpenAlexFDO

Authors Jittat Fakcharoenphol, Boonserm Kijsirikul

Publication date 7 September 2010

Published in Information Processing Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ipl.2010.02.008

zbMATH Keywords

analysis of algorithmson-line algorithmson-line learningprediction on graphs

Mathematics Subject Classification ID

Graph theory (including graph drawing) in computer science (68R10) Analysis of algorithms (68W40)

Recommendations

• Predicting a switching sequence of graph labelings
• The one-inclusion graph algorithm is near-optimal for the prediction model of learning
• scientific article; zbMATH DE number 1453050
• Exploiting Cluster-Structure to Predict the Labeling of a Graph
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning

Cites work

• scientific article; zbMATH DE number 3420728 (Why is no real title available?)
• Computing and Combinatorics
• Erratum: Constructing Multiclass Learners from Binary Learners: A Simple Black-Box Analysis of the Generalization Errors
• Exploiting Cluster-Structure to Predict the Labeling of a Graph

Cited in

(2)

• Exploiting Cluster-Structure to Predict the Labeling of a Graph
• Predicting a switching sequence of graph labelings

This page was built for publication: Short proofs for online multiclass prediction on graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q991792)