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

DOI10.3150/19-BEJ1143MaRDI QIDQ2295028zbMATH OpenOpenAlexFDO

Authors Giacomo Aletti, Irene Crimaldi, Andrea Ghiglietti

Publication date 12 February 2020

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1811.10255, https://projecteuclid.org/euclid.bj/1580461574

zbMATH Keywords

asymptotic normalitycomplex networksinteracting random systemsreinforced learningreinforced stochastic processessynchronizationurn modelsweighted empirical means

Mathematics Subject Classification ID

Strong limit theorems (60F15) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Asymptotic properties of parametric estimators (62F12)

Abstract: This work deals with a system 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 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 $heqj$, 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 characterizes the asymptotic behavior of the weighted empirical means $N_{n,j}=su{m}_{k=1}^n{q}_{n,k}{X}_{k,j}$, proving their almost sure synchronization and some central limit theorems in the sense of stable convergence. By means of a more sophisticated decomposition of the considered processes adopted here, these findings complete and improve some asymptotic results for the personal inclinations $Z^j=(Z_{n,j}{)}_n$ and for the empirical means $overline{X}^j=(su{m}_{k=1}^n{X}_{k,j}/n{)}_n$ given in recent papers (e.g. [arXiv:1705.02126, Bernoulli, Forth.]; [arXiv:1607.08514, Ann. Appl. Probab., 27(6):3787-3844, 2017]; [arXiv:1602.06217, Stochastic Process. Appl., 129(1):70-101, 2019]). Our work is motivated by the aim to understand how the different rates of convergence of the involved stochastic processes combine and, from an applicative point of view, by the construction of confidence intervals for the common limit inclination of the agents and of 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 [arXiv:1705.02126, Bernoulli, Forth.]

Recommendations

• Networks of reinforced stochastic processes: asymptotics for the empirical means
• Synchronization in interacting reinforced stochastic processes
• Synchronization of reinforced stochastic processes with a network-based interaction
• Interacting reinforced-urn systems
• Interacting nonlinear reinforced stochastic processes: Synchronization or non-synchronization

Cites work

• A central limit theorem and its applications to multicolor randomly reinforced urns
• A Gaussian process approximation for two-color randomly reinforced urns
• A generalized Pólya's urn with graph based interactions
• A generalized Pólya's urn with graph based interactions: convergence at linearity
• A Polya Contagion Model for Networks
• A Strong Form of Stable Convergence
• A survey of random processes with reinforcement
• Asymptotics for randomly reinforced urns with random barriers
• Central limit theorem for an adaptive randomly reinforced urn model
• Central limit theorems for a hypergeometric randomly reinforced urn
• Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms
• Convergence results for multivariate martingales
• Dynamics of an adaptive randomly reinforced urn
• Fluctuation theorems for synchronization of interacting Pólya's urns
• Graph-based Pólya's urn: completion of the linear case
• scientific article; zbMATH DE number 5693631 (Why is no real title available?)
• scientific article; zbMATH DE number 3723610 (Why is no real title available?)
• Interacting generalized Friedman's urn systems
• Interacting reinforced-urn systems
• Networks of reinforced stochastic processes: asymptotics for the empirical means
• Nonparametric covariate-adjusted response-adaptive design based on a functional urn model
• On a notion of partially conditionally identically distributed sequences
• On a preferential attachment and generalized Pólya's urn model
• On generalized Pólya urn models
• Polya Urn Models
• Randomized urn models revisited using stochastic approximation
• Statistical properties of two-color randomly reinforced urn design targeting fixed allocations
• Synchronization and functional central limit theorems for interacting reinforced random walks
• Synchronization of reinforced stochastic processes with a network-based interaction
• Synchronization via interacting reinforcement

Cited in

(12)

• Vertex reinforced random walks with exponential interaction on complete graphs
• Generalized rescaled Pólya urn and its statistical application
• The rescaled Pólya urn: local reinforcement and chi-squared goodness-of-fit test
• Interacting urns on a finite directed graph
• MATRIX-MFO tandem workshop: Stochastic reinforcement processes and graphs. Abstracts from the MATRIX-MFO tandem workshop held March 5--10, 2023
• Interacting nonlinear reinforced stochastic processes: Synchronization or non-synchronization
• Networks of reinforced stochastic processes: probability of asymptotic polarization and related general results
• Synchronization and fluctuations for interacting stochastic systems with individual and collective reinforcement
• Networks of reinforced stochastic processes: a complete description of the first-order asymptotics
• Pólya urns on hypergraphs
• Reinforced dynamics for interacting agents in competitive or cooperative environments
• Central limit theorems for interacting innovation processes, related statistical tools and general results

This page was built for publication: Interacting reinforced stochastic processes: statistical inference based on the weighted empirical means

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2295028)