New bounds on the price of bandit feedback for mistake-bounded online multiclass learning

DOI10.1016/J.TCS.2019.11.017MaRDI QIDQ2290693zbMATH OpenOpenAlexFDO

Authors Philip M. Long

Publication date 29 January 2020

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2019.11.017

zbMATH Keywords

bandit feedbacklearning theorymistake-bound modelonline learning

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Optimal stopping in statistics (62L15) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27)

Recommendations

• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• A note on the price of bandit feedback for mistake-bounded online learning
• Sharp bounds on the price of bandit feedback for several models of mistake-bounded online learning
• Multiclass classification with bandit feedback using adaptive regularization
• Multiclass learnability and the ERM principle

Cites work

• 10.1162/153244303321897663
• Apple tasting.
• scientific article; zbMATH DE number 3048068 (Why is no real title available?)
• scientific article; zbMATH DE number 3106671 (Why is no real title available?)
• Multiclass classification with bandit feedback using adaptive regularization
• On the complexity of function learning
• Pairwise independence and derandomization.
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Reinforcement learning with immediate rewards and linear hypotheses
• Structural results about on-line learning models with and without queries
• The Nonstochastic Multiarmed Bandit Problem
• The weighted majority algorithm

Cited in

(8)

• Multiclass classification with bandit feedback using adaptive regularization
• A note on the price of bandit feedback for mistake-bounded online learning
• Mistake bounds on the noise-free multi-armed bandit game
• 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
• Multiclass learnability and the ERM principle
• Sharp bounds on the price of bandit feedback for several models of mistake-bounded online learning
• Short proofs for online multiclass prediction on graphs

This page was built for publication: New bounds on the price of bandit feedback for mistake-bounded online multiclass learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2290693)