Iterated logarithmic expansions of the pathwise code lengths for exponential families

IEEE Transactions on Information Theory

Volumn 46, Issue 7, 2000, Pages 2683-2689

  Li, Lei ^a,c   Yu, Bin ^b  

^a FLORIDA STATE UNIVERSITY   (United States)

^b LUCENT TECHNOLOGIES   (United States)

^c UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BOUNDARY CONDITIONS; COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; ENCODING (SYMBOLS); ITERATIVE METHODS; MATRIX ALGEBRA; MAXIMUM LIKELIHOOD ESTIMATION; POLYNOMIAL APPROXIMATION; PROBABILITY DENSITY FUNCTION; PROBABILITY DISTRIBUTIONS; STATISTICAL METHODS; VECTORS;

EXPONENTIAL FAMILIES; ITERATED LOGARITHMIC EXPANSIONS; MINIMUM DESCRIPTION LENGTH; MIXTURE CODES; PATHWISE CODE LENGTH; PREDICTIVE CODES;

CODES (SYMBOLS);

EID: 0034318594     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/18.887882     Document Type: Article

References (21)

1. A. Barren, J. Rissanen, and B. Yu, The minimum description length principle in coding and modeling, IEEE. Trans. Inform. Theory, vol. 44, pp. 2743-2760, Oct. 1998.
2. A. R. Barron and N. Hengartner, Information theory and superefficiency, Ann. Statist., to be published.
3. L. D. Brown, Fundamentals of Statistical Exponential Families: With Applications in Statistical Decision Theory. Hayward, CA: Inst. Math. Statist., 1987.
4. N. G. De Bruijn, Asymptotic Methods in Analysis. Amsterdam, The Netherlands: North-Holland, 1958.
5. B. S. Clarke and A. R. Barron, Information-theoretic asymptotics of Bayesian methods, IEEE Trans. Inform. Theory, vol. 36, pp. 453-471, May 1990.
6. Jeffrey" prior is asymptotically least favorable under entropy risk, J. Statist. Planning and Inference, vol. 41, pp. 37-64, 1994.
7. A. P. Dawid, Present position and potential developments: Some personal views, statistical theory, the prequential approach, J. Roy. Statist. Soc. Ser. B, p. 147, 1984.
8. Prequential analysis, stochastic complexity and Bayesian inference," in 4th Valencia Int. Meet. Bayesian Statistics, 1992, pp. 15-20.
9. R. Durrett, Probability: Theory and Examples. Pacific Grove, CA: Wadsworth & Brooks/Cole, 1991.
10. T. S. Ferguson, Bayesian density estimation via mixtures of normal distributions," in Recent Advances in Statistics. New York: Academic, 1983, pp. 287-302.
11. Y Freund, Predicting a binary sequence almost as well as the optimal biased coin," unpublished manuscript.
12. P. Hall and C. C. Heyde, Martingale Limit Theorem and Its Application. New York, London: Academic, 1980.
13. M. Hansen and B. Yu, Model selection and minimum description length principle, JASA, submitted for publication.
14. M. J. D. Powell, Approximation Theory and Methods. Cambridge, U.K.: Cambridge Univ. Press, 1981.
15. J. Rissanen, Modeling by shortest data description, Automatica, vol. 14, pp. 465-171, 1978.
16. A predictive least squares principle, IMA J. Math. Contr. Inform., vol. 3, pp. 211-222, 1986.
17. Stochastic complexity and modeling," Ann. Statist., vol. 14, pp. 1080-1100, 1986.
18. Stochastic Complexity and Statistical Inquiry. Singapore: World Scientific, 1989.
19. Fisher information and stochastic complexity, IEEE Trans. Inform. Theory, vol. 42, pp. 40-47, Jan. 1996.
20. J. Takeuchi and A. R. Barron, Asymptotically minimax regret by Bayesian mixtures," in Proc. IEEE Int. Symp. Information Theory, Cambridge, MA, Aug. 1988, p. 318.
21. L. Tierney and J. B. Kadane, Accurate approximations for posterior moments and marginal densities, J. Amer. Statist. Assoc., vol. 81, pp. 82-86, 1986.