## Bernoulli

• Bernoulli
• Volume 25, Number 4B (2019), 3339-3378.

### Networks of reinforced stochastic processes: Asymptotics for the empirical means

#### Abstract

This work deals with systems of interacting reinforced stochastic processes, where each process $X^{j}=(X_{n,j})_{n}$ is located at a vertex $j$ of a finite weighted direct graph, and it can be interpreted as the sequence of “actions” adopted by an agent $j$ of the network. The interaction among the evolving dynamics of these processes depends on the weighted adjacency matrix $W$ associated to the underlying graph: indeed, the probability that an agent $j$ chooses a certain action depends on its personal “inclination” $Z_{n,j}$ and on the inclinations $Z_{n,h}$, with $h\neq j$, of the other agents according to the elements of $W$.

Asymptotic results for the stochastic processes of the personal inclinations $Z^{j}=(Z_{n,j})_{n}$ have been subject of studies in recent papers (e.g., Aletti, Crimaldi and Ghiglietti [Ann. Appl. Probab. 27 (2017) 3787–3844], Crimaldi et al. [Synchronization and functional central limit theorems for interacting reinforced random walks (2019)]); while the asymptotic behavior of quantities based on the stochastic processes $X^{j}$ of the actions has never been studied yet. In this paper, we fill this gap by characterizing the asymptotic behavior of the empirical means $N_{n,j}=\sum_{k=1}^{n}X_{k,j}/n$, proving their almost sure synchronization and some central limit theorems in the sense of stable convergence. Moreover, we discuss some statistical applications of these convergence results concerning confidence intervals for the random limit toward which all the processes of the system almost surely converge and tools to make inference on the matrix $W$.

#### Article information

Source
Bernoulli, Volume 25, Number 4B (2019), 3339-3378.

Dates
Revised: May 2018
First available in Project Euclid: 25 September 2019

Permanent link to this document
https://projecteuclid.org/euclid.bj/1569398768

Digital Object Identifier
doi:10.3150/18-BEJ1092

Mathematical Reviews number (MathSciNet)
MR4010957

Zentralblatt MATH identifier
07110140

#### Citation

Aletti, Giacomo; Crimaldi, Irene; Ghiglietti, Andrea. Networks of reinforced stochastic processes: Asymptotics for the empirical means. Bernoulli 25 (2019), no. 4B, 3339--3378. doi:10.3150/18-BEJ1092. https://projecteuclid.org/euclid.bj/1569398768

#### References

• [1] Albert, R. and Barabási, A.-L. (2002). Statistical mechanics of complex networks. Rev. Modern Phys. 74 47–97.
• [2] Aletti, G., Crimaldi, I. and Ghiglietti, A. (2019). Supplement to “Networks of reinforced stochastic processes: asymptotics for the empirical means.” DOI:10.3150/18-BEJ1092SUPP.
• [3] Aletti, G., Crimaldi, I. and Ghiglietti, A. (2017). Synchronization of reinforced stochastic processes with a network-based interaction. Ann. Appl. Probab. 27 3787–3844.
• [4] Aletti, G. and Ghiglietti, A. (2017). Interacting generalized Friedman’s urn systems. Stochastic Process. Appl. 127 2650–2678.
• [5] Aletti, G., Ghiglietti, A. and Vidyashankar, A.N. (2018). Dynamics of an adaptive randomly reinforced urn. Bernoulli 24 2204–2255.
• [6] Aletti, G., May, C. and Secchi, P. (2009). A central limit theorem, and related results, for a two-color randomly reinforced urn. Adv. in Appl. Probab. 41 829–844.
• [7] Arenas, A., Díaz-Guilera, A., Kurths, J., Moreno, Y. and Zhou, C. (2008). Synchronization in complex networks. Phys. Rep. 469 93–153.
• [8] Barabási, A.-L. and Albert, R. (1999). Emergence of scaling in random networks. Science 286 509–512.
• [9] Benaïm, M., Benjamini, I., Chen, J. and Lima, Y. (2015). A generalized Pólya’s urn with graph based interactions. Random Structures Algorithms 46 614–634.
• [10] Berti, P., Crimaldi, I., Pratelli, L. and Rigo, P. (2011). A central limit theorem and its applications to multicolor randomly reinforced urns. J. Appl. Probab. 48 527–546.
• [11] Berti, P., Crimaldi, I., Pratelli, L. and Rigo, P. (2016). Asymptotics for randomly reinforced urns with random barriers. J. Appl. Probab. 53 1206–1220.
• [12] Chen, J. and Lucas, C. (2014). A generalized Pólya’s urn with graph based interactions: Convergence at linearity. Electron. Commun. Probab. 19 no. 67, 13.
• [13] Chen, M.-R. and Kuba, M. (2013). On generalized Pólya urn models. J. Appl. Probab. 50 1169–1186.
• [14] Cirillo, P., Gallegati, M. and Hüsler, J. (2012). A Pólya lattice model to study leverage dynamics and contagious financial fragility. Adv. Complex Syst. 15 1250069, 26.
• [15] Collevecchio, A., Cotar, C. and LiCalzi, M. (2013). On a preferential attachment and generalized Pólya’s urn model. Ann. Appl. Probab. 23 1219–1253.
• [16] Crimaldi, I. (2009). An almost sure conditional convergence result and an application to a generalized Pólya urn. Int. Math. Forum 4 1139–1156.
• [17] Crimaldi, I. (2016). Central limit theorems for a hypergeometric randomly reinforced urn. J. Appl. Probab. 53 899–913.
• [18] Crimaldi, I. (2016). Introduzione Alla Nozione di Convergenza Stabile e sue Varianti (Introduction to the Notion of Stable Convergence and Its Variants) 57. Bologna, Italy: Unione Matematica Italiana, Monograf s.r.l. Book written in Italian.
• [19] Crimaldi, I., Dai Pra, P. and Minelli, I.G. (2016). Fluctuation theorems for synchronization of interacting Pólya’s urns. Stochastic Process. Appl. 126 930–947.
• [20] Crimaldi, I., Dai Pra, P., Louis, P.Y. and Minelli, I.G. (2019). Synchronization and functional central limit theorems for interacting reinforced random walks. Stochastic Process. Appl. 129 70–101.
• [21] Crimaldi, I., Letta, G. and Pratelli, L. (2007). A strong form of stable convergence. In Séminaire de Probabilités XL. Lecture Notes in Math. 1899 203–225. Berlin: Springer.
• [22] Crimaldi, I. and Pratelli, L. (2005). Convergence results for multivariate martingales. Stochastic Process. Appl. 115 571–577.
• [23] Dai Pra, P., Louis, P.-Y. and Minelli, I.G. (2014). Synchronization via interacting reinforcement. J. Appl. Probab. 51 556–568.
• [24] Fortini, S., Petrone, S. and Sporysheva, P. (2018). On a notion of partially conditionally identically distributed sequences. Stochastic Process. Appl. 128 819–846.
• [25] Ghiglietti, A. and Paganoni, A.M. (2014). Statistical properties of two-color randomly reinforced urn design targeting fixed allocations. Electron. J. Stat. 8 708–737.
• [26] Ghiglietti, A., Vidyashankar, A.N. and Rosenberger, W.F. (2017). Central limit theorem for an adaptive randomly reinforced urn model. Ann. Appl. Probab. 27 2956–3003.
• [27] Hall, P. and Heyde, C.C. (1980). Martingale Limit Theory and Its Application: Probability and Mathematical Statistics. New York-London: Academic Press.
• [28] Konda, V.R. and Tsitsiklis, J.N. (2004). Convergence rate of linear two-time-scale stochastic approximation. Ann. Appl. Probab. 14 796–819.
• [29] Laruelle, S. and Pagès, G. (2013). Randomized urn models revisited using stochastic approximation. Ann. Appl. Probab. 23 1409–1436.
• [30] Lima, Y. (2016). Graph-based Pólya’s urn: Completion of the linear case. Stoch. Dyn. 16 1660007, 13.
• [31] Mokkadem, A. and Pelletier, M. (2006). Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algorithms. Ann. Appl. Probab. 16 1671–1702.
• [32] Newman, M.E.J. (2010). Networks: An Introduction. Oxford: Oxford Univ. Press.
• [33] Paganoni, A.M. and Secchi, P. (2004). Interacting reinforced-urn systems. Adv. in Appl. Probab. 36 791–804.
• [34] Pelletier, M. (1998). Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing. Ann. Appl. Probab. 8 10–44.
• [35] Pemantle, R. (2007). A survey of random processes with reinforcement. Probab. Surv. 4 1–79.
• [36] van der Hofstad, R. (2016). Random Graphs and Complex Networks. https://www.win.tue.nl/~rhofstad/NotesRGCN.html.
• [37] Zhang, L.-X. (2014). A Gaussian process approximation for two-color randomly reinforced urns. Electron. J. Probab. 19 no. 86, 19.

#### Supplemental materials

• Supplement to “Networks of reinforced stochastic processes: Asymptotics for the empirical means”. This supplementary file provides the proofs of the technical lemmas and some computations used in Section 4.