Inferring interaction rules from observations of evolutive systems I: The variational approach

DOI10.1142/S0218202517500208zbMath1368.37017arXiv1602.00342MaRDI QIDQ2988719

Markus Hansen, Massimo Fornasier, Mattia Bongini, Mauro Maggioni

Publication date: 19 May 2017

Published in: Mathematical Models and Methods in Applied Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1602.00342

zbMATH Keywords

\(\Gamma\)-convergence; mean-field equation; first-order nonlocal interaction equation; nonlocal interaction kernel learning

Mathematics Subject Classification ID

68Q32: Computational learning theory

93B30: System identification

49N45: Inverse problems in optimal control

37A60: Dynamical aspects of statistical mechanics

97M70: Behavioral and social sciences (aspects of mathematics education)

49N30: Problems with incomplete information (optimization)

Related Items

Learning interacting particle systems: Diffusion parameter estimation for aggregation equations, Unnamed Item, Mean-field Analysis of Multipopulation Dynamics with Label Switching, Leader formation with mean-field birth and death models, Learning Interaction Kernels in Mean-Field Equations of First-Order Systems of Interacting Particles, Numerical Identification of Nonlocal Potentials in Aggregation, Robust Identification of Differential Equations by Numerical Techniques from a Single Set of Noisy Observation, Particle Based gPC Methods for Mean-Field Models of Swarming with Uncertainty, Learning theory for inferring interaction kernels in second-order interacting agent systems, Reproducing kernel Hilbert spaces in the mean field limit, On the coercivity condition in the learning of interacting particle systems, Robust feedback stabilization of interacting multi-agent systems under uncertainty, Identifiability of interaction kernels in mean-field equations of interacting particles, Learning and sparse control of multiagent systems, On the identifiability of interaction functions in systems of interacting particles, IDENT: identifying differential equations with numerical time evolution, Maximum likelihood estimation of potential energy in interacting particle systems from single-trajectory data, Parameter calibration with stochastic gradient descent for interacting particle systems driven by neural networks, Data-driven discovery of emergent behaviors in collective dynamics, Applications of optimal transportation in the natural sciences. Abstracts from the workshop held February 21--27, 2021 (online meeting), Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories, Learning mean-field equations from particle data using WSINDy, Inferring interaction rules from observations of evolutive systems I: The variational approach

Uses Software

• CVX

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Consistency of probability measure quantization by means of power repulsion-attraction potentials
• Constructive quantization: approximation by empirical measures
• Chemical oscillations, waves, and turbulence
• New statistical tools for analyzing the structure of animal groups
• An introduction to \(\Gamma\)-convergence
• Multiscale modeling of pedestrian dynamics
• Universal algorithms for learning theory. II: Piecewise polynomial functions
• Particle Systems and Kinetic Equations Modeling Interacting Agents in High Dimension
• Mean-Field Optimal Control
• Inferring interaction rules from observations of evolutive systems I: The variational approach
• A WELL-POSEDNESS THEORY IN MEASURES FOR SOME KINETIC MODELS OF COLLECTIVE MOTION
• Graph Implementations for Nonsmooth Convex Programs
• Particle, kinetic, and hydrodynamic models of swarming
• Emergent Behavior in Flocks