On asymptotically optimal methods of prediction and adaptive coding for Markov sources

DOI10.1006/JCOM.2001.0611zbMath0992.62092OpenAlexW2141636183MaRDI QIDQ1599202

Flemming Topsøe, Boris Ya. Ryabko

Publication date: 20 September 2002

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jcom.2001.0611

zbMATH Keywords

predictionuniversal codingepsilon-netadaptive codingimaginary sliding windowepsilon-capacity

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Source coding (94A29)

Related Items (3)

Universal codes as a basis for time series testing ⋮ Universal codes as a basis for nonparametric testing of serial independence for time series ⋮ Experimental investigation of forecasting methods based on data compression algorithms

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Prediction of random sequences and universal coding
• The complexity and effectiveness of prediction algorithms
• Data compression using an ``imaginary sliding window
• On the computational power of pushdown automata
• Universal coding, information, prediction, and estimation
• Universal prediction of individual sequences
• A fast on-line adaptive code
• Optimal finite memory learning algorithms for the finite sample problem
• Laplace's law of succession and universal encoding
• Fifty years of Shannon theory
• Universal prediction
• Universal schemes for learning the best nonlinear predictor given the infinite past and side information

This page was built for publication: On asymptotically optimal methods of prediction and adaptive coding for Markov sources