On the identifiability of interaction functions in systems of interacting particles
From MaRDI portal
Publication:1994899
Abstract: We address a fundamental issue in the nonparametric inference for systems of interacting particles: the identifiability of the interaction functions. We prove that the interaction functions are identifiable for a class of first-order stochastic systems, including linear systems with general initial laws and nonlinear systems with stationary distributions. We show that a coercivity condition is sufficient for identifiability and becomes necessary when the number of particles approaches infinity. The coercivity is equivalent to the strict positivity of related integral operators, which we prove by showing that their integral kernels are strictly positive definite by using M"untz type theorems.
Recommendations
- Learning theory for inferring interaction kernels in second-order interacting agent systems
- Nonparametric inference of interaction laws in systems of agents from trajectory data
- Inferring interaction rules from observations of evolutive systems I: The variational approach
- Eigenfunction Martingale Estimators for Interacting Particle Systems and Their Mean Field Limit
- scientific article; zbMATH DE number 1112364
Cites work
- Convergence to equilibrium for granular media equations and their Euler schemes
- Emergence of time-asymptotic flocking in a stochastic Cucker-Smale system
- Geometry on probability spaces
- Heterophilious dynamics enhances consensus
- scientific article; zbMATH DE number 4004880 (Why is no real title available?)
- scientific article; zbMATH DE number 149872 (Why is no real title available?)
- scientific article; zbMATH DE number 1984450 (Why is no real title available?)
- scientific article; zbMATH DE number 933353 (Why is no real title available?)
- scientific article; zbMATH DE number 3100102 (Why is no real title available?)
- Inferring interaction rules from observations of evolutive systems I: The variational approach
- Learning interacting particle systems: diffusion parameter estimation for aggregation equations
- Müntz-type theorems on the half-line with weights
- Nonlocal aggregation models: a primer of swarm equilibria
- Nonparametric inference of interaction laws in systems of agents from trajectory data
- On the mathematical foundations of learning
- On the mean field limit for Brownian particles with Coulomb interaction in 3D
- On the regularity of many-particle dynamical systems perturbed by white noise
- Probabilistic approach for granular media equations in the non-uniformly convex case
- Propagation of chaos for large Brownian particle system with Coulomb interaction
- Properties equivalent to the completeness of {𝑒^{-𝑡}𝑡^{𝜆_{𝑛}}}
- Stability of regime-switching stochastic differential equations
- Statistical inference for ergodic diffusion processes.
- Stochastic Cucker-Smale models: old and new
- The generalized Bernstein problem on weighted lacunary polynomial approximation
- The methods of distances in the theory of probability and statistics.
Cited in
(19)- Maximum likelihood estimation of potential energy in interacting particle systems from single-trajectory data
- The LAN property for McKean-Vlasov models in a mean-field regime
- Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories
- Learning mean-field equations from particle data using WSINDy
- Learning interaction kernels in heterogeneous systems of agents from multiple trajectories
- Learning Interaction Kernels in Mean-Field Equations of First-Order Systems of Interacting Particles
- Nonparametric inference of interaction laws in systems of agents from trajectory data
- Learning theory for inferring interaction kernels in second-order interacting agent systems
- Nonparametric adaptive estimation for interacting particle systems
- On the coercivity condition in the learning of interacting particle systems
- Identifiability of interaction kernels in mean-field equations of interacting particles
- Unsupervised learning of observation functions in state space models by nonparametric moment methods
- A method of moments estimator for interacting particle systems and their mean field limit
- On the identifiability of nonlocal interaction kernels in first-order systems of interacting particles on Riemannian manifolds
- Inference for ergodic McKean-Vlasov stochastic differential equations with polynomial interactions
- Nonparametric moment method for scalar McKean-Vlasov stochastic differential equations
- Kernel-algorithms in frame-approximations
- Sparse identification of nonlocal interaction kernels in nonlinear gradient flow equations via partial inversion
- Interacting particle systems on networks: joint inference of the network and the interaction kernel
This page was built for publication: On the identifiability of interaction functions in systems of interacting particles
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1994899)
