Abstract
We give a development of the ODE method for the analysis of recursive algorithms described by a stochastic recursion. With variability modeled via an underlying Markov process, and under general assumptions, the following results are obtained:
-
(i)
Stability of an associated ODE implies that the stochastic recursion is stable in a strong sense when a gain parameter is small.
-
(ii)
The range of gain-values is quantified through a spectral analysis of an associated linear operator, providing a non-local theory, even for nonlinear systems.
-
(iii)
A second-order analysis shows precisely how variability leads to sensitivity of the algorithm with respect to the gain parameter.
All results are obtained within the natural operator-theoretic framework of geometrically ergodic Markov processes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
L. Arnold. Random dynamical systems. Springer-Verlag, Berlin, 1998.
S. Balaji and S.P. Meyn. Multiplicative ergodicity and large deviations for an irreducible Markov chain. Stochastic Process. Appl., 90(1):123–144, 2000.
R. Bellman. Limit theorems for non-commutative operations. I. Duke Math. J., 21, 1954.
Michel Benaïm. Dynamics of stochastic approximation algorithms. In Séminaire de Probabilités, XXXIII, pages 1–68. Springer, Berlin, 1999.
Albert Benveniste, Michel Métivier, and Pierre Priouret. Adaptive algorithms and stochastic approximations. Springer-Verlag, Berlin, 1990. Translated from the French by Stephen S. Wilson.
D.P. Bertsekas and J. Tsitsiklis. Neuro-Dynamic Programming. Atena Scientific, Cambridge, Mass, 1996.
B. Bharath and V. S. Borkar. Stochastic approximation algorithms: overview and recent trends. Sāadhanā, 24(4–5):425–452, 1999. Chance as necessity.
V.S. Borkar and S.P. Meyn. The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning. SIAM J. Control Optim., 38:447–69, 2000.
P. Bougerol. Limit theorem for products of random matrices with Markovian dependence. In Proceedings of the 1st World Congress of the Bernoulli Society, Vol. 1 (Tashkent, 1986), pages 767–770, Utrecht, 1987. VNU Sci. Press.
A. Crisanti, G. Paladin, and A. Vulpiani. Products of random matrices in statistical physics. Springer-Verlag, Berlin, 1993.
O. Dabeer and E. Masry. The LMS adaptive algorithm: Asymptotic error analysis. In Proceedings of the 34th Annual Conference on Information Sciences and Systems, CISS 2000, pages WP1-6–WP1-7, Princeton, NJ, March 2000.
Paul Fischer and Hans Ulrich Simon, editors. Computational learning theory, Berlin, 1999. Springer-Verlag. Lecture Notes in Artificial Intelligence.
H. Furstenberg and H. Kesten. Products of random matrices. Ann. Math. Statist, 31:457–469, 1960.
László Gerencsér. Almost sure exponential stability of random linear differential equations. Stochastics Stochastics Rep., 36(2):91–107, 1991.
R. Gharavi and V. Anantharam. Structure theorems for partially asynchronous iterations of a nonnegative matrix with random delays. Sādhanā, 24(4–5):369–423, 1999. Chance as necessity.
S.V. Hanly and D. Tse. Multiaccess fading channels. II. Delay-limited capacities. IEEE Trans. Inform. Theory, 44(7):2816–2831, 1998.
J. A. Joslin and A. J. Heunis. Law of the iterated logarithm for a constant-gain linear stochastic gradient algorithm. SIAM J. Control Optim., 39(2):533–570 (electronic), 2000.
I. Kontoyiannis and S.P. Meyn. Spectral theory and limit theorems for geometrically ergodic Markov processes. Submitted, 2001. Also presented at the 2001 INFORMS Applied Probability Conference, NY, July, 2001.
I. Kontoyiannis and S.P. Meyn. Spectral theory and limit theorems for geometrically ergodic Markov processes. Part II: Empirical measures & unbounded functionals. Preprint, 2001.
H. J. Kushner. Approximation and weak convergence methods for random processes, with applications to stochastic systems theory. MIT Press, Cambridge, MA, 1984.
H.J. Kushner and G. Yin. Stochastic approximation algorithms and applications. Springer-Verlag, New York, 1997.
L. Ljung. On positive real transfer functions and the convergence of some recursive schemes. IEEE Trans. Automatic Control, AC-22(4):539–551, 1977.
Jean Mairesse. Products of irreducible random matrices in the (max, +) algebra. Adv. in Appl. Probab., 29(2):444–477, 1997.
M. Medard, S.P. Meyn, and J. Huang. Capacity benefits from channel sounding in Rayleigh fading channels. INFOCOM (submitted), 2001.
S. P. Meyn and R. L. Tweedie. Markov Chains and Stochastic Stability. Springer-Verlag, London, 1993.
S.P. Meyn and R.L. Tweedie. Computable bounds for geometric convergence rates of Markov chains. Ann. Appl. Probab., 4(4):981–1011, 1994.
G.V. Moustakides. Exponential convergence of products of random matrices, application to the study of adaptive algorithms. International Journal of Adaptive Control and Signal Processing, 2(12):579–597, 1998.
V. I. Oseledec. Markov chains, skew products and ergodic theorems for “general” dynamic systems. Teor. Verojatnost. i Primenen., 10:551–557, 1965.
V. I. Oseledec. A multiplicative ergodic theorem. Characteristic Ljapunov, exponents of dynamical systems. Trudy Moskov. Mat. Obšč., 19:179–210, 1968.
J. B. T. M Roerdink. Products of random matrices or ”why do biennials live longer than two years? CWI Quarterly, 2:37–44, 1989.
E. Seneta. Non-negative Matrices and Markov Chains. Springer-Verlag, New York, Second edition, 1980.
H. Thorisson. Coupling, stationarity, and regeneration. Springer-Verlag, New York, 2000.
D. Tse and S.V. Hanly. Multiaccess fading channels. I. Polymatroid structure, optimal resource allocation and throughput capacities. IEEE Trans. Inform. Theory, 44(7):2796–2815, 1998.
Divakar Viswanath. Random Fibonacci sequences and the number 1.13198824.... Math. Comp., 69(231):1131–1155, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Huang, J., Kontoyiannis, I., Meyn, S.P. (2002). The ODE Method and Spectral Theory of Markov Operators. In: Pasik-Duncan, B. (eds) Stochastic Theory and Control. Lecture Notes in Control and Information Sciences, vol 280. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48022-6_15
Download citation
DOI: https://doi.org/10.1007/3-540-48022-6_15
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43777-2
Online ISBN: 978-3-540-48022-8
eBook Packages: Springer Book Archive