The LAN property for McKean-Vlasov models in a mean-field regime

DOI10.1016/J.SPA.2022.10.002zbMATH Open1504.60192arXiv2205.05932OpenAlexW4305072806MaRDI QIDQ2105067FDOQ2105067

Authors: Yanyan Li 

Publication date: 8 December 2022

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Abstract: We establish the local asymptotic normality (LAN) property for estimating a multidimensional parameter in the drift of a system of $N$ interacting particles observed over a fixed time horizon in a mean-field regime $Nightarrowinfty$. By implementing the classical theory of Ibragimov and Hasminski, we obtain in particular sharp results for the maximum likelihood estimator that go beyond its simple asymptotic normality thanks to H'ajek's convolution theorem and strong controls of the likelihood process that yield asymptotic minimax optimality (up to constants). Our structural results shed some light to the accompanying nonlinear McKean-Vlasov experiment, and enable us to derive simple and explicit criteria to obtain identifiability and non-degeneracy of the Fisher information matrix. These conditions are also of interest for other recent studies on the topic of parametric inference for interacting diffusions.

Full work available at URL: https://arxiv.org/abs/2205.05932

Recommendations

• Maximum Likelihood Theory for Large Interacting Systems
• Online parameter estimation for the McKean-Vlasov stochastic differential equation
• Parametric inference for small variance and long time horizon McKean-Vlasov diffusion models
• scientific article; zbMATH DE number 1112364
• LAN and LAMN for systems of interacting diffusions with branching and immigration

zbMATH Keywords

maximum likelihood estimationparametric estimationinteracting particle systemsLAN propertyMcKean-Vlasov modelsstatistics and PDE

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Markov processes: estimation; hidden Markov models (62M05) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Minimax procedures in statistical decision theory (62C20) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10)

Cites Work

• Identification in Parametric Models
• Title not available (Why is that?)
• Title not available (Why is that?)
• On an aggregation model with long and short range interactions
• Stochastic mean-field limit: non-Lipschitz forces and swarming
• Title not available (Why is that?)
• A CLASS OF MARKOV PROCESSES ASSOCIATED WITH NONLINEAR PARABOLIC EQUATIONS
• On the estimation of the diffusion coefficient for multi-dimensional diffusion processes
• A non-local model for a swarm
• LAN and LAMN for systems of interacting diffusions with branching and immigration
• Mean-field description and propagation of chaos in networks of Hodgkin-Huxley and FitzHugh-Nagumo neurons
• On the rate of convergence in Wasserstein distance of the empirical measure
• Discretization of processes.
• Title not available (Why is that?)
• Central limit theorem for a simple diffusion model of interacting particles
• Nonlinear reflecting diffusion process, and the propagation of chaos and fluctuations associated
• Title not available (Why is that?)
• Title not available (Why is that?)
• An Eulerian approach to the analysis of Krause's consensus models
• Quantitative concentration inequalities for empirical measures on non-compact spaces
• Fokker-Planck-Kolmogorov equations
• A law of large numbers for moderately interacting diffusion processes
• Minimum contrast estimation in fractional Ornstein-Uhlenbeck process: continuous and discrete sampling
• Title not available (Why is that?)
• The Master Equation and the Convergence Problem in Mean Field Games
• Probabilistic theory of mean field games with applications I. Mean field FBSDEs, control, and games
• Well-posedness of the limiting equation of a noisy consensus model in opinion dynamics
• On a strong form of propagation of chaos for McKean-Vlasov equations
• Maximum likelihood estimation of McKean-Vlasov stochastic differential equation and its application
• Parameter estimation of path-dependent McKean-Vlasov stochastic differential equations
• Mean field game of controls and an application to trade crowding
• Maximum Likelihood Theory for Large Interacting Systems
• On the identifiability of interaction functions in systems of interacting particles
• Inference for large financial systems
• Maximum likelihood estimation of potential energy in interacting particle systems from single-trajectory data
• Nonparametric estimation for interacting particle systems: McKean-Vlasov models
• Parametric inference for small variance and long time horizon McKean-Vlasov diffusion models
• Probabilistic properties and parametric inference of small variance nonlinear self-stabilizing stochastic differential equations
• Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories
• Title not available (Why is that?)
• Learning Interaction Kernels in Mean-Field Equations of First-Order Systems of Interacting Particles

Cited In (11)

• Parametric inference for ergodic McKean-Vlasov stochastic differential equations
• Learning theory for inferring interaction kernels in second-order interacting agent systems
• Online parameter estimation for the McKean-Vlasov stochastic differential equation
• LAN and LAMN for systems of interacting diffusions with branching and immigration
• On the identifiability of nonlocal interaction kernels in first-order systems of interacting particles on Riemannian manifolds
• Identifiability of interaction kernels in mean-field equations of interacting particles
• Parameter estimation of discretely observed interacting particle systems
• Maximum likelihood estimation of potential energy in interacting particle systems from single-trajectory data
• Eigenfunction Martingale Estimators for Interacting Particle Systems and Their Mean Field Limit
• Inference for ergodic McKean-Vlasov stochastic differential equations with polynomial interactions
• A method of moments estimator for interacting particle systems and their mean field limit

This page was built for publication: The LAN property for McKean-Vlasov models in a mean-field regime

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2105067)