Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring

DOI10.1007/11894841_20MaRDI QIDQ3522989zbMATH OpenOpenAlexFDO

Authors Chamy Allenberg, Peter Auer, László Györfi, György Ottucsàk

Publication date 4 September 2008

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/11894841_20

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Inference from stochastic processes and prediction (62M20)

Recommendations

• Online learning in case of unbounded losses using follow the perturbed leader algorithm
• Partial monitoring -- classification, regret bounds, and algorithms
• Regret Minimization Under Partial Monitoring
• How to better use expert advice
• The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses

Cited in

(8)

• Algorithm portfolio selection as a bandit problem with unbounded losses
• Learning Volatility of Discrete Time Series Using Prediction with Expert Advice
• The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses
• Small-Loss Bounds for Online Learning with Partial Information
• Learning Theory
• Minimizing Regret With Label Efficient Prediction
• Strategies for Prediction Under Imperfect Monitoring
• Dismemberment and design for controlling the replication variance of regret for the multi-armed bandit

This page was built for publication: Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3522989)