This work deals with a system of interacting reinforced stochastic processes, where each process X-j = (X-n,X-j )(n), is located at a vertex j of a finite weighted directed graph, and it can be interpreted as the sequence of "actions" adopted by an agent j of the network. The interaction among the 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 not equal j, of the other agents according to the entries of W. The best known example of reinforced stochastic process is the Polya urn. The present paper focuses on the weighted empirical means N-n,N-j = Sigma(n)(k)(=1) q(n,k) X-k,X- j, since, for example, the current experience is more important than the past one in reinforced learning. Their almost sure synchronization and some central limit theorems in the sense of stable convergence are proven. The new approach with weighted means highlights the key points in proving some recent results for the personal inclinations Z(j) = (Z(n,j))(n) and for the empirical means (X) over bar (j) = (Sigma(n)(k)(=1) X-k,X- j/n)(n) given in recent papers (e.g. Aletti, Crimaldi and Ghiglietti (2019), Ann. Appl. Probab. 27 (2017) 3787-3844, Crimaldi et al. Stochastic Process. Appl. 129 (2019) 70-101). In fact, with a more sophisticated decomposition of the considered processes, we can understand how the different convergence rates of the involved stochastic processes combine. From an application point of view, we provide confidence intervals for the common limit inclination of the agents and a test statistics to make inference on the matrix W, based on the weighted empirical means. In particular, we answer a research question posed in Aletti, Crimaldi and Ghiglietti (2019).

Interacting reinforced stochastic processes: Statistical inference based on the weighted empirical means / G. Aletti, I. Crimaldi, A. Ghiglietti. - In: BERNOULLI. - ISSN 1350-7265. - 26:2(2020 May), pp. 1098-1138. [10.3150/19-BEJ1143]

Interacting reinforced stochastic processes: Statistical inference based on the weighted empirical means

G. Aletti
Primo
;
A. Ghiglietti
Ultimo
2020

Abstract

This work deals with a system of interacting reinforced stochastic processes, where each process X-j = (X-n,X-j )(n), is located at a vertex j of a finite weighted directed graph, and it can be interpreted as the sequence of "actions" adopted by an agent j of the network. The interaction among the 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 not equal j, of the other agents according to the entries of W. The best known example of reinforced stochastic process is the Polya urn. The present paper focuses on the weighted empirical means N-n,N-j = Sigma(n)(k)(=1) q(n,k) X-k,X- j, since, for example, the current experience is more important than the past one in reinforced learning. Their almost sure synchronization and some central limit theorems in the sense of stable convergence are proven. The new approach with weighted means highlights the key points in proving some recent results for the personal inclinations Z(j) = (Z(n,j))(n) and for the empirical means (X) over bar (j) = (Sigma(n)(k)(=1) X-k,X- j/n)(n) given in recent papers (e.g. Aletti, Crimaldi and Ghiglietti (2019), Ann. Appl. Probab. 27 (2017) 3787-3844, Crimaldi et al. Stochastic Process. Appl. 129 (2019) 70-101). In fact, with a more sophisticated decomposition of the considered processes, we can understand how the different convergence rates of the involved stochastic processes combine. From an application point of view, we provide confidence intervals for the common limit inclination of the agents and a test statistics to make inference on the matrix W, based on the weighted empirical means. In particular, we answer a research question posed in Aletti, Crimaldi and Ghiglietti (2019).
asymptotic normality; complex networks; interacting random systems; reinforced learning; reinforced stochastic processes; synchronization; urn models; weighted empirical means;
Settore MAT/06 - Probabilita' e Statistica Matematica
Settore SECS-S/01 - Statistica
mag-2020
Centro di Ricerca Interdisciplinare su Modellistica Matematica, Analisi Statistica e Simulazione Computazionale per la Innovazione Scientifica e Tecnologica ADAMSS
http://hdl.handle.net/2434/607869
Article (author)
File in questo prodotto:
File Dimensione Formato  
euclid.bj.1580461574.pdf

accesso aperto

Descrizione: Aricle
Tipologia: Publisher's version/PDF
Dimensione 363.49 kB
Formato Adobe PDF
363.49 kB Adobe PDF Visualizza/Apri
euclid.bj.1580461574_suppl.pdf

accesso aperto

Descrizione: Supplementary matherial
Tipologia: Altro
Dimensione 394.71 kB
Formato Adobe PDF
394.71 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/709000
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 8
social impact