Twofold universal prediction schemes for achieving the finite-state predictability of a noisy individual binary sequence

IEEE Transactions on Information Theory

Volumn 47, Issue 5, 2001, Pages 1849-1866

  Weissman, T ^a   Merhav, N ^a   Somekh Baruch, A ^a  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

Finite state (FS) predictability; Individual sequences; Martingales; Prediction with noise; Universal prediction

Indexed keywords

ACOUSTIC NOISE; CHANNEL CAPACITY; FINITE AUTOMATA; SIGNAL FILTERING AND PREDICTION; STORAGE ALLOCATION (COMPUTER);

BINARY-SYMMETRIC CHANNELS (BSC); FINITE-STATE (FS) PREDICTORS;

BINARY SEQUENCES;

EID: 0035397523     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/18.930923     Document Type: Article

References (47)

1. On sequential prediction of individual sequences relative to a set of experts
2. How to use expert advice
3. A theory of program size formally identical to information theory
4. Universal portfolios
5. Compound Bayes predictors for sequences with apparent Markov structure
6. Gambling using a finite-state machine
7. Universal prediction of individual sequences
8. Asymptotic solutions of the compound decision problem for two completely specified distributions
9. Sequential prediction of individual sequences under general loss functions
10. Three approaches to the quantitative definition of information
11. Universal prediction
12. Universal coding with minimum probability of codeword length overflow
13. Universal schemes for sequential decision from individual data sequences
14. The k-extended set-compound estimation problem in nonregular family of distributions
15. Worst case prediction over sequences under log loss
16. The functional law of the iterated logarithm for stationary strongly mixing sequences
17. Universal coding, information, prediction, and estimation
18. Asymptotically subminimax solutions of compound statistical decision problems
19. Testing statistical hypotheses - The 'compound' approach
20. Encoding a source with unknown bur ordered probabilities
21. The sequential compound decision problem with m × n finite loss matrix
22. An empirical Bayes approach to the testing of certain parametric hypotheses
23. Asymptotic solutions of the sequential compound decision problem
24. Convergence of the losses of certain decision rules for the sequential compound decision problem
25. On simple rules for the compound decision problem
26. Note on a sequential classification problem
27. Sequential compound estimators
28. The compound decision problem in the opponent case
29. A formal theory of inductive inference, pt. 1
30. A martingale analogue of Kolmogorov's law of the iterated logarithm
31. The Hartman-Wintner law of the iterated logarithm for Martingales
32. Admissible solutions of k-extended finite state set and the sequence compound decision problems
33. A game of prediction with expert advice
34. Aggregating strategies
35. Optimal sequential probability assignment for individual sequences
36. On prediction of individual sequences relative to a set of experts in the presence of noise
37. Universal prediction of individual binary sequences in the presence of arbitrarily varying, memoryless additive noise
38. Universal prediction of individual binary sequences in the presence of noise
39. A theorem on the entropy of certain binary sequences and applications: Part I
40. Compression of individual sequences via variable rate coding