Universal prediction of random binary sequences in a noisy environment

DOI10.1214/aoap/1075828047zbMath1040.62085OpenAlexW2025310275MaRDI QIDQ1431550

Neri Merhav, Tsachy Weissman

Publication date: 10 June 2004

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aoap/1075828047

zbMATH Keywords

filteringasymptotic optimalityShannon entropysequential decisionsmartingale differenceconditional mixinguniversal predictiongeneralized ergodic theoremprediction with expertsprediction with noise

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Statistical decision theory (62C99) Sequential statistical analysis (62L10) Statistical aspects of information-theoretic topics (62B10) Prediction theory (aspects of stochastic processes) (60G25)

Related Items (2)

Ergodicity, Decisions, and Partial Information ⋮ On universal estimates for binary renewal processes

Cites Work

• Unnamed Item
• Unnamed Item
• Robust Wiener filters
• A note on minimax filtering
• Lyapunov Exponents for Finite State Nonlinear Filtering
• Minimax-robust prediction of discrete time series
• Robust Wiener filtering for multiple inputs with channel distortion (Corresp.)
• Robust Wiener- Kolmogorov theory
• Robust techniques for signal processing: A survey
• Universal prediction of individual sequences
• Compression of individual sequences via variable-rate coding
• A simple randomized algorithm for sequential prediction of ergodic time series
• Twofold universal prediction schemes for achieving the finite-state predictability of a noisy individual binary sequence
• Universal prediction of individual binary sequences in the presence of noise
• Sequential prediction of individual sequences under general loss functions
• Universal prediction
• The strong law of large numbers for sequential decisions under uncertainty

This page was built for publication: Universal prediction of random binary sequences in a noisy environment