Multiclass online learnability under bandit feedback

MaRDI QIDQ7017074zbMATH OpenFDO

Authors Ananth Raman, Vinod Raman, Unique Subedi, Ambuj Tewari

Publication date 6 March 2025

Full work available at URL https://proceedings.mlr.press/v237/raman24a.html

zbMATH Keywords

bandit feedbackmulticlass classificationonline learnability

Mathematics Subject Classification ID

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

Cites work

• A characterization of multiclass learnability
• A note on the price of bandit feedback for mistake-bounded online learning
• Adversarial laws of large numbers and optimal regret in online classification
• scientific article; zbMATH DE number 3446442 (Why is no real title available?)
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• Online learning via sequential complexities
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Sequential complexities and uniform martingale laws of large numbers
• Structural results about on-line learning models with and without queries

This page was built for publication: Multiclass online learnability under bandit feedback

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7017074)