Multiclass classification with bandit feedback using adaptive regularization

DOI10.1007/S10994-012-5321-8MaRDI QIDQ1945036zbMATH OpenOpenAlexFDO

Authors Koby Crammer, Claudio Gentile

Publication date 28 March 2013

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-012-5321-8

zbMATH Keywords

online learningregretupper confidence bound

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27)

Recommendations

• scientific article
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• Multi-class AdaBoost
• Multi-Class Random Matrix Filtering for Adaptive Learning
• Active learning with adaptive regularization
• Multi-kernel regularized classifiers

Cites work

• 10.1162/153244303321897663
• 10.1162/jmlr.2003.3.4-5.951
• A Second-Order Perceptron Algorithm
• Bandit problems with side observations
• On the learnability and design of output codes for multiclass problems
• Relative loss bounds for on-line density estimation with the exponential family of distributions
• Ridge Regression: Biased Estimation for Nonorthogonal Problems

Cited in

(4)

• Sharp bounds on the price of bandit feedback for several models of mistake-bounded online learning
• scientific article; zbMATH DE number 6378144 (Why is no real title available?)
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning

Describes a project that uses

Uses Software

• RCV1

This page was built for publication: Multiclass classification with bandit feedback using adaptive regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1945036)