Achievability of asymptotic minimax regret by horizon-dependent and horizon-independent strategies

MaRDI QIDQ5744841zbMATH OpenFDO

Authors Kazuho Watanabe, Teemu Roos

Publication date 19 February 2016

Full work available at URL http://jmlr.csail.mit.edu/papers/v16/watanabe15a.html

zbMATH Keywords

asymptotic minimax regretBayes mixturenormalized maximum likelihoodonline learningprediction of individual sequences

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20) Point estimation (62F10)

Recommendations

• Asymptotic minimax regret for data compression, gambling, and prediction
• Regret bounds and minimax policies under partial monitoring
• Minimax optimal Bayes mixtures for memoryless sources over large alphabets
• On asymptotic and finite-time optimality of Bayesian predictors
• Minimax and bates strategies for the discounted infinite horizon one-armed-bandit.—explicit formulae and structural properties

Cited in

(3)

• Asymptotic minimax regret for data compression, gambling, and prediction
• Minimax optimal Bayes mixtures for memoryless sources over large alphabets
• Minimum description length revisited

This page was built for publication: Achievability of asymptotic minimax regret by horizon-dependent and horizon-independent strategies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5744841)