Asymptotic minimax regret for data compression, gambling, and prediction

DOI10.1109/18.825803zbMath0996.94025OpenAlexW2122056749MaRDI QIDQ4503538

Qun Xie, Andrew R. Barron

Publication date: 7 September 2000

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

Full work available at URL: https://semanticscholar.org/paper/2fc09d1d7562dfcc313e35f55e197b7f56ddaacd

zbMATH Keywords

minimax regretuniversal codinguniversal predictionJeffrey's priorminimax redundance

Mathematics Subject Classification ID

Other game-theoretic models (91A40) Stochastic games, stochastic differential games (91A15) Source coding (94A29)

Related Items (16)

Interpreting uninterpretable predictors: kernel methods, Shtarkov solutions, and random forests ⋮ Information optimality and Bayesian modelling ⋮ Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory ⋮ A linear-time algorithm for computing the multinomial stochastic complexity ⋮ Using the Bayesian Shtarkov solution for predictions ⋮ Competitive On-line Statistics ⋮ On model selection, Bayesian networks, and the Fisher information integral ⋮ A Bayesian approach to (online) transfer learning: theory and algorithms ⋮ Optimal, reliable estimation of quantum states ⋮ Predicting a binary sequence almost as well as the optimal biased coin ⋮ Asymptotically minimax Bayesian predictive densities for multinomial models ⋮ When does ambiguity fade away? ⋮ Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor ⋮ Unnamed Item ⋮ A lower bound on compression of unknown alphabets ⋮ Prequential analysis of complex data with adaptive model reselection

This page was built for publication: Asymptotic minimax regret for data compression, gambling, and prediction