Predicting a binary sequence almost as well as the optimal biased coin

DOI10.1016/S0890-5401(02)00033-0zbMath1028.68116MaRDI QIDQ1398365

Yoav Freund

Publication date: 29 July 2003

Published in: Information and Computation (Search for Journal in Brave)

zbMATH Keywords

Bayes algorithmJeffrey's prior

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (3)

Generalization bounds for averaged classifiers ⋮ Predicting a binary sequence almost as well as the optimal biased coin ⋮ Regret to the best vs. regret to the average

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An analog of the minimax theorem for vector payoffs
• Universal sequential coding of single messages
• A game of prediction with expert advice
• The weighted majority algorithm
• Jeffreys' prior is asymptotically least favorable under entropy risk
• Predicting a binary sequence almost as well as the optimal biased coin
• On prediction of individual sequences
• Regret in the on-line decision problem
• Prediction in the worst case
• Universal modeling and coding
• Universal prediction of individual sequences
• Minimax redundancy for the class of memoryless sources
• A general minimax result for relative entropy
• Universal Portfolios
• Asymptotic minimax regret for data compression, gambling, and prediction
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• A decision-theoretic extension of stochastic complexity and its applications to learning
• The minimum description length principle in coding and modeling
• Universal noiseless coding
• The context-tree weighting method: basic properties
• Fisher information and stochastic complexity
• Universal portfolios with side information
• How to use expert advice
• Periodic Sigma Functions

This page was built for publication: Predicting a binary sequence almost as well as the optimal biased coin