On the coercivity condition in the learning of interacting particle systems

DOI10.1142/S0219493723400038MaRDI QIDQ6151507zbMATH OpenOpenAlexFDO

Authors

Publication date 11 March 2024

Published in Stochastics and Dynamics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2011.10480

zbMATH Keywords

ergodicityidentifiabilityinverse problempositive definite kernelstochastic particle systemperturbation schemefinite-dimensional hypothesis subspace

Mathematics Subject Classification ID

Inverse problems for systems of particles (70F17) Random and stochastic aspects of the mechanics of particles and systems (70L99)

Abstract: In the learning of systems of interacting particles or agents, coercivity condition ensures identifiability of the interaction functions, providing the foundation of learning by nonparametric regression. The coercivity condition is equivalent to the strictly positive definiteness of an integral kernel arising in the learning. We show that for a class of interaction functions such that the system is ergodic, the integral kernel is strictly positive definite, and hence the coercivity condition holds true.

Recommendations

• On the identifiability of interaction functions in systems of interacting particles
• Learning theory for inferring interaction kernels in second-order interacting agent systems
• Inferring interaction rules from observations of evolutive systems I: The variational approach
• Learning interaction kernels in heterogeneous systems of agents from multiple trajectories
• A method of moments estimator for interacting particle systems and their mean field limit

Cites work

• 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 7370549 (Why is no real title available?)
• Convergence to equilibrium for granular media equations and their Euler schemes
• Heterophilious dynamics enhances consensus
• Inferring interaction rules from observations of evolutive systems I: The variational approach
• Kinetic equilibration rates for granular media and related equations: entropy dissipation and mass transportation estimates
• Learning Interaction Kernels in Mean-Field Equations of First-Order Systems of Interacting Particles
• Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories
• Learning theory for inferring interaction kernels in second-order interacting agent systems
• Maximum likelihood estimation of potential energy in interacting particle systems from single-trajectory data
• Nonparametric inference of interaction laws in systems of agents from trajectory data
• On the identifiability of interaction functions in systems of interacting particles
• On the mathematical foundations of learning
• On the trend to equilibrium for some dissipative systems with slowly increasing a priori bounds.
• Randomized sketches for kernels: fast and optimal nonparametric regression
• The methods of distances in the theory of probability and statistics.

This page was built for publication: On the coercivity condition in the learning of interacting particle systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6151507)