Context tree selection: A unifying view

Stochastic Processes and their Applications

Volumn 121, Issue 11, 2011, Pages 2488-2506

  Garivier, A ^a   Leonardi, F ^b  

^a INSTITUT TELECOM   (France)

^b UNIVERSITY OF SÃO PAULO   (Brazil)

Author keywords

Algorithm Context; Bayesian information criterion; Deviation inequalities; Model selection; Penalized maximum likelihood; Variable length Markov chains

Indexed keywords

BAYESIAN INFORMATION CRITERION; DEVIATION INEQUALITIES; MODEL SELECTION; PENALIZED MAXIMUM LIKELIHOOD; VARIABLE LENGTH MARKOV CHAINS;

ALGORITHMS; ASYMPTOTIC ANALYSIS; ESTIMATION; MARKOV PROCESSES; PLANT EXTRACTS; PROBABILITY; TREES (MATHEMATICS);

MAXIMUM LIKELIHOOD ESTIMATION;

EID: 80052493272     PISSN: 03044149     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.spa.2011.06.012     Document Type: Article

References (27)

1. A. Barron, J. Rissanen, and B. Yu The minimum description length principle in coding and modeling IEEE Trans. Inform. Theory 44 6 1998 2743 2760 Information theory: 19481998 (Pubitemid 128741906)
2. G. Bejerano, and G. Yona Variations on probabilistic suffix trees: statistical modeling and prediction of protein families Bioinformatics 17 1 2001 23 43 (Pubitemid 32178011)
3. L. Breiman, J.H. Friedman, R.A. Olshen, and C.J. Stone Classification and Regression Trees Wadsworth Statistics/Probability Series 1984 Wadsworth Advanced Books and Software Belmont, CA
4. P. Bhlmann, and A.J. Wyner Variable length Markov chains Ann. Statist. 27 1999 480 513
5. J.R. Busch, P.A. Ferrari, A.G. Flesia, R. Fraiman, S.P. Grynberg, and F. Leonardi Testing statistical hypothesis on random trees and applications to the protein classification problem Ann. Appl. Stat. 3 2 2009
6. N. Cesa-Bianchi, and G. Lugosi Prediction, Learning, and Games 2006 Cambridge University Press Cambridge
7. F. Comets, R. Fernández, and P. Ferrari Processes with long memory: regenerative construction and perfect simulation Ann. Appl. Probab. 12 3 2002 921 943 (Pubitemid 37023736)
8. I. Csiszár Large-scale typicality of Markov sample paths and consistency of MDL order estimators IEEE Trans. Inform. Theory 48 6 2002 1616 1628 Special issue on Shannon theory: perspective, trends, and applications (Pubitemid 34759864)
9. I. Csiszár, and Z. Talata Context tree estimation for not necessarily finite memory processes, via BIC and MDL IEEE Trans. Inform. Theory 52 3 2006 1007 1016 (Pubitemid 46444888)
10. I. Csiszár, and Z. Talata On rate of convergence of statistical estimation of stationary ergodic processes IEEE Trans. Inform. Theory 56 8 2010 3637 3641
11. J. Dedecker, and C. Prieur New dependence coefficients. Examples and applications to statistics Probab. Theory Related Fields 132 2005 203 236 (Pubitemid 43300514)
12. D. Duarte, A. Galves, and N.L. Garcia Markov approximation and consistent estimation of unbounded probabilistic suffix trees Bull. Braz. Math. Soc. 37 4 2006 581 592
13. R. Fernández, and A. Galves Markov approximations of chains of infinite order Bull. Braz. Math. Soc. 33 3 2002 295 306 (Pubitemid 36507600)
14. S. Filippi, O. Cappé, A. Garivier, Optimism in reinforcement learning based on KullbackLeibler divergence, in: 48th Annual Allerton Conference on Communication, Control, and Computing, 2010.
15. A. Galves, C. Galves, J. Garcia, N.L. Garcia, F. Leonardi, Context tree selection and linguistic rhythm retrieval from written texts, 2010, pp. 125. ArXiv:0902.3619.
16. A. Galves, A. Garivier, E. Gassiat, Data selection of context trees and classification, Technical Report, 2010.
17. A. Galves, and F. Leonardi Exponential Inequalities for Empirical Unbounded Context Trees Progress in Probability vol. 60 2008 Birkhauser 257 270
18. A. Galves, V. Maume-Deschamps, and B. Schmitt Exponential inequalities for VLMC empirical trees ESAIM Probab. Stat. 12 2008 43 45
19. A. Garivier Consistency of the unlimited BIC context tree estimator IEEE Trans. Inform. Theory 52 10 2006 4630 4635 (Pubitemid 46445298)
20. A. Garivier, O. Cappé, The KL-UCB algorithm for bounded stochastic bandits and beyond, in: 23rd Conf. Learning Theory, COLT, Budapest, Hungary, 2011.
21. A. Garivier, E. Moulines, On upper-confidence bound policies for non-stationary bandit problems, 2008. arxiv.org:0805.3415.
22. F. Leonardi Some upper bounds for the rate of convergence of penalized likelihood context tree estimators Braz. J. Probab. Stat. 24 2 2010 321 336
23. P. Massart Concentration Inequalities and Model Selection Lecture Notes in Mathematics vol. 1896 2007 Springer Berlin Lectures from the 33rd Summer School on Probability Theory held in Saint-Flour, July 623, 2003, With a foreword by Jean Picard
24. J. Neveu Martingales Temps Discret 1972 Masson
25. J. Rissanen A universal data compression system IEEE Trans. Inform. Theory 29 5 1983 656 664
26. Z. Talata, T. Duncan, Unrestricted BIC context tree estimation for not necessarily finite memory processes, in: Information Theory, 2009. ISIT 2009. IEEE International Symposium on, 28 2009-July 3 2009, pp. 724728.
27. F.M.J. Willems, Y.M. Shtarkov, and T.J. Tjalkens The context-tree weighting method: basic properties IEEE Trans. Inf. Theory 41 3 1995 653 664