## Stochastic Systems

### Moderate deviations for recursive stochastic algorithms

#### Abstract

We prove a moderate deviation principle for the continuous time interpolation of discrete time recursive stochastic processes. The methods of proof are somewhat different from the corresponding large deviation result, and in particular the proof of the upper bound is more complicated.

#### Article information

Source
Stoch. Syst., Volume 5, Number 1 (2015), 87-119.

Dates
First available in Project Euclid: 23 December 2015

https://projecteuclid.org/euclid.ssy/1450879282

Digital Object Identifier
doi:10.1214/14-SSY138

Mathematical Reviews number (MathSciNet)
MR3442390

Zentralblatt MATH identifier
1335.60050

#### Citation

Dupuis, Paul; Johnson, Dane. Moderate deviations for recursive stochastic algorithms. Stoch. Syst. 5 (2015), no. 1, 87--119. doi:10.1214/14-SSY138. https://projecteuclid.org/euclid.ssy/1450879282

#### References

• [1] Azencott, R. and Ruget, G. (1977). Mélanges d’équations differentielles et grand écart à la loi des grandes nombres. Z. Wahrsch. Verw. Gebiete 38 1–54.
• [2] Baldi, P. (1988). Large deviations and stochastic homogenization. Ann. Mat. Pura Appl. 151 161–177.
• [3] Blanchet, J.H., Glynn, P. and Leder, K. (2012). On Lyapunov inequalities and subsolutions for efficient importance sampling. TOMACS 22 Article No. 13.
• [4] Boué, M. and Dupuis, P. (1998). A variational representation for certain functionals of Brownian motion. Ann. Probab. 26 1641–1659.
• [5] Budhiraja, A., Dupuis, P. and Maroulas, V. (2011). Variational representations for continuous time processes. Ann. de l’Inst. H. Poincaré 47 725–747.
• [6] Chen, X. and de Acosta, A. (1998). Moderate deviations for empirical measures of Markov chains: Upper bounds. J. Theor. Probab. 11 1075–1110.
• [7] de Acosta, A. (1997). Moderate deviations for empirical measures of Markov chains: Lower bounds. Ann. Probab. 25 259–284.
• [8] Dean, T. and Dupuis, P. (2009). Splitting for rare event simulation: A large deviations approach to design and analysis. Stoch. Proc. Appl. 119 562–587.
• [9] Dembo, A. (1996) Moderate deviations for martingales with bounded jumps. Elect. Comm. Probab. 1 11–17.
• [10] Dembo, A. and Zeitouni, O. (1993). Large Deviations Techniques and Applications. Jones and Bartlett, Boston.
• [11] Djellout, H. (2002). Moderate deviations for martingale differences and applications to $\phi$-mixing sequences. Stoch. Stoch. Rep. 73 37–63.
• [12] Dupuis, P. and Ellis, R. S. (1997). A Weak Convergence Approach to the Theory of Large Deviations. John Wiley & Sons, New York.
• [13] Dupuis, P. and Wang, H. (2004). Importance sampling, large deviations, and differential games. Stoch. Stoch. Reports. 76 481–508.
• [14] Dupuis, P. and Wang, H. (2007). Subsolutions of an Isaacs equation and efficient schemes for importance sampling. Math. Oper. Res. 32 1–35.
• [15] Freidlin, M. I. and Wentzell, A. D. (1984). Random Perturbations of Dynamical Systems. Springer-Verlag, New York.
• [16] Gao, F.Q. (1996). Moderate deviations for martingales and mixing random processes. Stoch. Proc. Appl. 61 263–275.
• [17] Guillin, A. (2001). Moderate deviations of inhomogeneous functionals of Markov processes and application to averaging. Stoch. Proc. Appl. 92 287–313.
• [18] Guillin, A. (2003). Averaging principle of SDE with small diffusion: Moderate deviations. Ann. Probab. 31 413–443.
• [19] Horn, R. A. and Johnson, C. R. (1991). Topics in Matrix Analysis. Cambridge University Press, New York, New York.
• [20] Wentzell, A.D. (1976). Rough limit theorems on large deviations for Markov stochastic processes, I. Theory Probab. Appl. 21 227–242.
• [21] Wentzell, A.D. (1976). Rough limit theorems on large deviations for Markov stochastic processes, II. Theory Probab. Appl. 21 499–512.
• [22] Wentzell, A.D. (1979). Rough limit theorems on large deviations for Markov stochastic processes, III. Theory Probab. Appl. 24 675–692.
• [23] Wentzell, A.D. (1982). Rough limit theorems on large deviations for Markov stochastic processes, IV. Theory Probab. Appl. 27 215–234.