Advertisement

Geometric & Functional Analysis GAFA

, Volume 6, Issue 3, pp 556–571 | Cite as

A measure concentration inequality for contracting markov chains

  • K. Marton
Article

Abstract

The concentration of measure phenomenon in product spaces means the following: if a subsetA of then'th power of a probability space Χ does not have too small a probability then very large probability is concentrated in a small neighborhood ofA. The neighborhood is in many cases understood in the sense of Hamming distance, and then measure concentration is known to occur for product probability measures, and also for the distribution of some processes with very fast and uniform decay of memory. Recently Talagrand introduced another notion of neighborhood of sets for which he proved a similar measure concentration inequality which in many cases allows more efficient applications than the one for a Hamming neighborhood. So far this inequality has only been proved for product distributions. The aim of this paper is to give a new proof of Talagrand's inequality, which admits an extension to contracting Markov chains. The proof is based on a new asymmetric notion of distance between probability measures, and bounding this distance by informational divergence. As an application, we analyze the bin packing problem for Markov chains.

Keywords

Markov Chain Probability Measure Similar Measure Measure Concentration Probability Space 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [B]
    L. Breiman, Probability, Addison-Wesley, Reading, Massachusetts, 1968.Google Scholar
  2. [AGK]
    R. Ahlswede, P. Gács, J. Körner, Bounds on conditional probabilities with applications in multi-user communication, Zeitschrift f. Wahrscheinlichkeitstheorie u. verw. Geb. 34 (1976), 157–177.Google Scholar
  3. [AmMi]
    D. Amir, V. Milman, Unconditional symmetric sets inn-dimensional normed spaces, Israel J. of Math. 37 (1980), 3–20.Google Scholar
  4. [C]
    I. Csiszár, Information type measures of difference of probability distributions and indirect observations, Studia Sci. Math. Hung. 2 (1967), 297–318.Google Scholar
  5. [CK]
    I. Csiszár, J. Körner, Information Theory: Coding Theorems for Discrete Memoryless Systems, Academic Press, Inc., New York, London etc. 1981.Google Scholar
  6. [Ku]
    S. Kullback, Information Theory and Statistics, Wiley & Son, New York, London etc. 1959.Google Scholar
  7. [M1]
    K. Marton, A simple proof of the blowing-up lemma, IEEE Trans. on Information Theory IT-32 (1986), 445–446.Google Scholar
  8. [M2]
    K. Marton, Boundingd-distance by informational divergence: a way to prove measure concentration, Annals of Probability, to appear.Google Scholar
  9. [M3]
    K. Marton, Measure concentration for a class of random processes, manuscript.Google Scholar
  10. [Mc]
    C. McDiarmid, On the method of bounded differences, in “Surveys in Combinatorics” (J. Simons, ed.) London Mathematical Society Lecture Notes 141, Cambridge University Press, London-New York (1989), 148–188.Google Scholar
  11. [Mi]
    V. Milman, The heritage of P. Lévy in geometrical and functional analysis, Asterisque 157–158 (1988), 273–301.Google Scholar
  12. [P]
    M.S. Pinsker, Information and Information Stability of Random Variables and Processes, Holden-Day, San Francisco, 1964.Google Scholar
  13. [R1]
    W. Rhee, On the fluctuations of the stochastic traveling salesperson problem, Math. of Operations Research 16 (1991), 482–489.Google Scholar
  14. [R2]
    W. Rhee, A matching problem and subadditive Euclidean functionals, Ann. Applied Probab. 3 (1993), 794–801.Google Scholar
  15. [R3]
    W. Rhee, On the fluctuations of simple matching, manuscript (1992).Google Scholar
  16. [T1]
    M. Talagrand, An isoperimetric theorem on the cube and the Khintchine-Kahane inequalities, Proc. Amer. Math. Soc. 104 (1988), 905–909.Google Scholar
  17. [T2]
    M. Talagrand, Concentration of measure and isoperimetric inequalities in product spaces, Publications of IHES 81 (1995), 73–205.Google Scholar
  18. [T3]
    M. Talagrand, Private communication.Google Scholar

Copyright information

© Birkhäuser Verlag 1996

Authors and Affiliations

  • K. Marton
    • 1
  1. 1.Mathematical Institute of the Hungarian Academy of SciencesBudapestHungary

Personalised recommendations