Dependent noise for stochastic algorithms

• Autorzy: Doukhan P. , Brandierie O.
• Języki publikacji: EN

Abstrakty

EN

We introduce different ways of being dependent for the input noise of stochastic algorithms. We are aimed to prove that such innovations allow to use the ODE (ordinary differential equation) method. Illustrations to the linear regression frame and to the law of large numbers for triangular arrays of weighted dependent random variables are also given.

Słowa kluczowe

EN

stochastic approximation; ordinary differential equations; dependent noise; linear regression

• Wydawca: Wrocław University of Science and Technology
• Czasopismo: Probability and Mathematical Statistics
• Rocznik: 2004
• Tom: Vol. 24, Fasc. 2
• Strony: 381--399
• Opis fizyczny: Bibliogr. 24 poz.

Twórcy

autor

Doukhan P.

• ENSAE and Laboratory of Statistics, CREST Timbre J340, 3, avenue Pierre Larousse, 92240 Malakoff, France

autor

Brandierie O.

• Universitié de Paris Sud 11, Laboratoire de Mathématiques, Bât. 425, 91 405 Orsay, France

Bibliografia

• [1] M. Benaïm, A dynamical system approach to stochastic approximation, SIAM J. Control. Optim. 34 (2) (1996), pp. 437-472.
• [2] M. Benaïm and M. W. Hirsch, Dynamics of Morse-Smale urn processes, Ergodic Theory Dynamical Systems 15 (1995), pp. 1005-1030.
• [3] A. Benveniste, M. Métivier et P. Priouret, Algorithms adaptatifs et approximations stochastiques, Masson, 1987.
• [4] P. Billingsley, Probability and Measure, 2nd edition, Wiley, 1985.
• [5] H.-F. Chen, Stochastic Approximation and Its Applications, Nonconvex Optimization and Its Application, Vol. 64, Kluwer Academic Publishers, 1985.
• [6] Y. S. Chow, Some convergence theorems for independent random variables, Ann. Math. Statist. 36 (4) (1966), pp. 1293-1314; ibidem 37 (1966), pp. 1482-1493.
• [7] C. Coulon-Prieur and P. Doukhan, A triangular CLT for weakly dependent sequences, Statist. Probab. Lett. 47 (2000), pp. 61-68.
• [8] R. M. De Jong, A strong law of large numbers for triangular mixingale arrays, Statist. Probab. Lett. 27 (1996), pp. 1-9.
• [9] P. Dedecker and P. Doukhan, A new covariance inequality and applications, Stochastic Process. Appl. 106 (1) (2003), pp. 63-80.
• [10] B. Delyon, General convergence result on stochastic approximation, IEEE Trans. Automat. Control. 41 (1996), p. 9.
• [11] P. Doukhan, Models inequalities and limit theorems for stationary sequences, in: Theory and Applications of Lang Range Dependence, P. Doukhan et al. (Eds.), Birkhäuser, 2002, pp. 43-101.
• [12] P. Doukhan and S. Louhichi, A new weak dependence condition and applications to moment inequalities, Stochastic Process. Appl. 84 (1999), pp. 313-342.
• [13] M. Duflo, Algorithmes stochastiques, Collect. Math. Appl. 23, Springer, 1996.
• [14] M. Fréchet, Généralisation d'une inégalité de Minkowski, Bull. Inst. Internat. Statist. 35 (2) (1957), pp. 99-103.
• [15] S. Ghosal and T. K. Chandra, Complete convergence of martingale arrays, J. Theoret. Probab. 11 (3) (1998), pp. 621-631.
• [16] J. Hoffmann-Jørgensen, Sums of independent Banach space valued random variables, Studia Math. 52 (1974), pp. 159-186.
• [17] P. L. Hsu and H. Robbins, Complete convergence and the strong law of large numbers, Proc. Nat. Acad. Sci. 33 (1947), pp. 25-31.
• [18] G. D. Kersting, Some results on the asymptotic behavior of the Robbins-Monro procedure, Bull. Int. Statist. Inst. 47 (1977), pp. 327-335.
• [19] H. J. Kushner and D. S. Clark, Stochastic approximation for constrained and unconstrained systems, Appl. Math. Sci. 26, Springer, 1978.
• [20] D. Li, M. B. Rao, T. Jiang and X. Wang, Complete convergence and almost sure convergence of weighted sums of random variables, J. Theoret. Probab. 8 (1995), pp. 49-76.
• [21] D. L. Mcleish, A maximal inequality and dependent strong laws, Ann. Probab. 3 (1975), pp. 829-839.
• [22] M. Peligrad and S. Utev, Central limit theorem for linear processes, Ann. Probab. 25 (3) (1997), pp. 443-456.
• [23] E. G. Shixin, On the convergence of weighted sums of Lq-mixingale arrays, Acta Math. Hungar. 82 (1-2) (1999), pp. 113-120.
• [24] K. F. Yu, Complete convergence of weighted sums of martingale differences, J. Theoret. Probab. 3 (1990), pp. 339-347.