Concentration of the information in data with log-concave distributions

Annals of Probability

Volumn 39, Issue 4, 2011, Pages 1528-1543

  Bobkov, Sergey ^a   Madiman, Mokshay ^b  

^a University of Minnesota   (United States)

^b YALE UNIVERSITY   (United States)

Author keywords

Asymptotic equipartition property; Concentration; Entropy; Log concave distributions; Shannon Mcmillan Breiman theorem

Indexed keywords

EID: 80051655875     PISSN: 00911798     EISSN: None     Source Type: Journal    
DOI: 10.1214/10-AOP592     Document Type: Article

References (22)

1. ALGOET, P. H. and COVER, T. M. (1988). A sandwich proof of the Shannon-Mcmillan-Breiman theorem. Ann. Probab. 16 899-909.
2. BARLOW, R. E., MARSHALL, A. W. and PROSCHAN, F. (1963). Properties of probability distributions with monotone hazard rate. Ann. Math. Statist. 34 375-389.
3. BARRON, A. R. (1985). The strong ergodic theorem for densities: Generalized Shannon-McMillan-Breiman theorem. Ann. Probab. 13 1292-1303.
4. BOBKOV, S. (1996). Extremal properties of half-spaces for log-concave distributions. Ann. Probab. 24 35-48.
5. BOBKOV, S. G. (2003). Spectral gap and concentration for some spherically symmetric probability measures. In Geometric Aspects of Functional Analysis. Lecture Notes in Math. 1807 37-43. Springer, Berlin.
6. BOBKOV, S. G. and MADIMAN, M. (2010). The entropy per coordinate of a random vector is highly constrained under convexity conditions. IEEE Trans. Inform. Theory. To appear. Available at http://arxiv.org/abs/1006.2883.
7. BOBKOV, S. G. and MADIMAN, M. (2010). When can one invert Hölder's inequality? (and why one may want to). Preprint.
8. BORELL, C. (1973). Complements of Lyapunov's inequality. Math. Ann. 205 323-331.
9. BORELL, C. (1974). Convex measures on locally convex spaces. Ark. Mat. 12 239-252.
10. BREIMAN, L. (1957). The individual ergodic theorem of information theory. Ann. Math. Statist. 28 809-811.
11. BREIMAN, L. (1960) Ann. Math. Statist. 31 809-810.
12. COVER, T. M. and POMBRA, S. (1989). Gaussian feedback capacity. IEEE Trans. Inform. Theory 35 37-43.
13. KANNAN, R., LOVÁSZ, L. and SIMONOVITS, M. (1995). Isoperimetric problems for convex bodies and a localization lemma. Discrete Comput. Geom. 13 541-559.
14. KARLIN, S., PROSCHAN, F. and BARLOW, R. E. (1961). Moment inequalities of Pólya frequency functions. Pacific J. Math. 11 1023-1033.
15. KIEFFER, J. C. (1974). A simple proof of the Moy-Perez generalization of the Shannon-McMillan theorem. Pacific J. Math. 51 203-206.
16. KLARTAG, B. and MILMAN, V. D. (2005). Geometry of log-concave functions and measures. Geom. Dedicata 112 169-182.
17. LOVÁSZ, L. and SIMONOVITS, M. (1993). Random walks in a convex body and an improved volume algorithm. Random Structures Algorithms 4 359-412.
18. MCMILLAN, B. (1953). The basic theorems of information theory. Ann. Math. Statist. 24 196-219.
19. MOY, S.-T. C. (1961). Generalizations of Shannon-McMillan theorem. Pacific J. Math. 11 705-714.
20. OREY, S. (1985). On the Shannon-Perez-Moy theorem. In Particle Systems, Random Media and Large Deviations (Brunswick, Maine, 1984). Contemporary Mathematics 41 319-327. Amer. Math. Soc., Providence, RI.
21. PEREZ, A. (1964). Extensions of Shannon-McMillan's limit theorem to more general stochastic processes. In Trans. Third Prague Conf. Information Theory, Statist. Decision Functions, Random Processes (Liblice, 1962) 545-574. Publ. House Czech. Acad. Sci., Prague.
22. SHANNON, C. E. (1948). A mathematical theory of communication. Bell System Tech. J. 27 379-423, 623-656.