Extension of the PAC framework to finite and countable Markov Chains

IEEE Transactions on Information Theory

Volumn 49, Issue 1, 2003, Pages 338-345

  Gamarnik, David ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

Learning; Lyapunov function; Rapid mixing; Stationary distribution; Vapnik Chervonenkis (VC) dimension

Indexed keywords

COMPUTATIONAL COMPLEXITY; LEARNING SYSTEMS; LYAPUNOV METHODS; POLYNOMIALS; PROBABILITY;

COUNTABLE MARKOV CHAINS;

RANDOM PROCESSES;

EID: 0037265542     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIT.2002.806131     Document Type: Article

References (21)

1. D. Aldous and J. Fill, Reversible Markov Chains and Random Walks on Graphs. In preparation.
2. D. Aldous and U. Vazirani, "A Markovian extension of Valiant's learning model," in Proc. 31st Symp. Foundations of Computer Science, 1990, pp. 392-396.
3. S. Balajian and S. P. Meyn, "Multiplicative ergodicity and large deviations for an irreducible Markov chain," Stochastic Processes Their Applic., vol. 90, pp. 123-144, 2000.
4. M. Anthony and N. Biggs, Computational Learning Theory. Cambridge, U.K.: Cambridge Univ. Press, 1992.
5. P. Bartlett, P. Fischer, and K. Hoffgen, "Exploiting random walks for learning," in Proc. 7th ACM Conf. Computational Learning Theory, 1994.
6. D. Bertsimas, D. Gamarnik, and J. Tsitsiklis, "Performance of multiclass Markovian queueing networks via piecewise linear Lyapunov functions," Ann. Appl. Probab., vol. 11, no. 4, pp. 1384-1428, 2001.
7. K. L. Buescher and P. R. Kumar, "Learning by canonical smooth estimation, Part I: Simultaneous estimation," IEEE Trans. Automat. Contr., vol. 41, pp. 545-556, Apr. 1996.
8. _, "Learning by canonical smooth estimation, Part II: Learning and model complexity," IEEE Trans. Automat. Contr., vol. 41, pp. 557-569, Apr. 1996.
9. D. Gillman, "A Chernoff bound for random walks on expander graphs," SIAM J. Comput., vol. 27, no. 4, pp. 1203-1219, 1998.
10. J. M. Harrison, Brownian Motion and Stochastic Flow Systems. Melbourne, FL: Krieger, 1990.
11. M. Kearns and U. Vazirani, An Introduction to Computational Learning Theory. Cambridge, MA: MIT Press, 1994.
12. Y. Li, P. Long, and A. Srinivasan, "Improved bounds on the sample complexity of learning," in Proc. 11th ACM-SIAM Symp. Discrete Algorithms, 2000, pp. 309-318.
13. P. Long, "The complexity of learning according to two models of a drifting enviroment," in Proc. 11th ACM Conf. Computational Learning Theory, 1998, pp. 116-125.
14. R. Meir, "Performance bounds for nonlinear time series prediction," in Proc. 10th ACM Conf Computational Learning Theory, 1997, pp. 122-130.
15. S. P. Meyn and R. L. Tweedie, Markov Chains and Stochastic Stability. New York: Springer-Verlag, 1993.
16. _, "Computable bounds for geometric convergence rates of Markov chains," Ann. Appl. Probab., vol. 4, pp. 981-1011, 1994.
17. D. S. Modha and E. Masry, "Memory-universal prediction of stationary random processes," IEEE Trans. Inform. Theory, vol. 44, pp. 117-133, Jan. 1998.
18. A. Nobel, "A counterexample concerning uniform ergodic theorems for a class of functions," Statist. Probab. Lett., vol. 24, pp. 165-168, 1995.
19. A. Shwartz and A. Weiss, Large Deviations for Performance Analysis. London, U.K.: Chapman and Hall, 1995.
20. M. Talagrand, "Sharper bounds for Gaussian and empirical processes," Ann. Probab., vol. 22, pp. 28-76, 1994.
21. V. Vapnik, The Nature of Statistical Learning Theory. New York: Springer-Verlag, 1995.