Minimizing Regret With Label Efficient Prediction

DOI10.1109/TIT.2005.847729MaRDI QIDQ3546663zbMATH OpenWikidataFDO

Authors Nicolò Cesa-Bianchi, Gilles Stoltz, Gábor Lugosi

Publication date 21 December 2008

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TIT.2005.847729

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Inference from stochastic processes and prediction (62M20) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning Theory
• On prediction of individual sequences
• How to use expert advice
• Regret bounds and minimax policies under partial monitoring
• Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring

Cited in

(13)

• Fano's inequality for random variables
• Improved second-order bounds for prediction with expert advice
• Quadratic Error Minimization in a Distributed Environment with Privacy Preserving
• Adaptive and optimal online linear regression on ^1-balls
• Algorithm portfolio selection as a bandit problem with unbounded losses
• Knows what it knows: a framework for self-aware learning
• Learning Theory
• Tracking climate models
• Online learning over a finite action set with limited switching
• Partial monitoring -- classification, regret bounds, and algorithms
• Small-Loss Bounds for Online Learning with Partial Information
• Constant regret for sequence prediction with limited advice
• Regret minimization, willingness-to-accept-losses and framing

This page was built for publication: Minimizing Regret With Label Efficient Prediction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3546663)