Approximate Bayesian Inference using the Mean-Field Distribution - Archive ouverte HAL
Book Sections Year : 2022

Approximate Bayesian Inference using the Mean-Field Distribution

Abstract

This chapter focuses on dynamical systems admitting a mean-field limit distribution when the population's size tends to infinity, such as the flocking models presented in Carrillo et al. It introduces a numerical scheme to simulate the mean-field distribution, which is a partial differential transport equation solution. These simulations are used to simplify the likelihood distributions associated with Bayesian inference problems arising when the population is only partially observed. Population models may be used to assess, from data, the interaction laws governing the individual dynamics. The chapter discusses the statistical inference problems related to the study of symmetric systems. It focuses on the plant population model introduced by Schneider et al. which is taken as an example of systems leading to difficult inference problems when the size of the population is partially known. The chapter gives an illustration of simulations of the Schneider system under the mean-field approximation.
No file

Dates and versions

hal-04374332 , version 1 (05-01-2024)

Identifiers

Cite

Antonin Della Noce, Paul-Henry Cournède. Approximate Bayesian Inference using the Mean-Field Distribution. Data Analysis and Related Applications 1: Computational, Algorithmic and Applied Economic Data Analysis, Volume 9, 1, Wiley, 2022, 9781394165513. ⟨10.1002/9781394165513.ch24⟩. ⟨hal-04374332⟩
22 View
0 Download

Altmetric

Share

More