Data-driven discovery of emergent behaviors in collective dynamics
From MaRDI portal
Publication:2127368
Abstract: Particle- and agent-based systems are a ubiquitous modeling tool in many disciplines. We consider the fundamental problem of inferring interaction kernels from observations of agent-based dynamical systems given observations of trajectories, in particular for collective dynamical systems exhibiting emergent behaviors with complicated interaction kernels, in a nonparametric fashion, and for kernels which are parametrized by a single unknown parameter. We extend the estimators introduced in cite{PNASLU}, which are based on suitably regularized least squares estimators, to these larger classes of systems. We provide extensive numerical evidence that the estimators provide faithful approximations to the interaction kernels, and provide accurate predictions for trajectories started at new initial conditions, both throughout the ``training time interval in which the observations were made, and often much beyond. We demonstrate these features on prototypical systems displaying collective behaviors, ranging from opinion dynamics, flocking dynamics, self-propelling particle dynamics, synchronized oscillator dynamics, and a gravitational system. Our experiments also suggest that our estimated systems can display the same emergent behaviors of the observed systems, that occur at larger timescales than those used in the training data. Finally, in the case of families of systems governed by a parameterized family of interaction kernels, we introduce novel estimators that estimate the parameterized family of kernels, splitting it into a common interaction kernel and the action of parameters. We demonstrate this in the case of gravity, by learning both the ``common component and the dependency on mass, without any a priori knowledge of either one, from observations of planetary motions in our solar system.
Recommendations
- Nonparametric inference of interaction laws in systems of agents from trajectory data
- Inferring interaction rules from observations of evolutive systems I: The variational approach
- Learning theory for inferring interaction kernels in second-order interacting agent systems
- Nonlocal flocking dynamics: learning the fractional order of PDEs from particle simulations
- Kernel-based parameter estimation of dynamical systems with unknown observation functions
Cites work
- A conceptual model for milling formations in biological aggregates
- A conditional, collision-avoiding, model for swarming
- A Cucker-Smale model with noise and delay
- A discrete nonlinear and non-autonomous model of consensus formation
- A distribution-free theory of nonparametric regression
- A General Collision-Avoiding Flocking Framework
- A Primer of Swarm Equilibria
- A simple proof of the Cucker-Smale flocking dynamics and mean-field limit
- Active particles, Volume 1. Advances in theory, models, and applications
- Approximation methods for supervised learning
- Avoiding Collisions in Flocks
- Clustering and asymptotic behavior in opinion formation
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Double milling in self-propelled swarms from kinetic theory
- Emergent Behavior in Flocks
- Eulerian dynamics with a commutator forcing
- Flocking in noisy environments
- From Kuramoto to Crawford: Exploring the onset of synchronization in population of coupled oscillators
- Heterophilious dynamics enhances consensus
- scientific article; zbMATH DE number 4072104 (Why is no real title available?)
- Hydrodynamic models of self-organized dynamics: derivation and existence theory
- Inferring interaction rules from observations of evolutive systems I: The variational approach
- Modeling opinion dynamics: how the network enhances consensus
- Nonparametric inference of interaction laws in systems of agents from trajectory data
- On collision-avoiding initial configurations to Cucker-Smale type flocking models
- On Krause's Multi-Agent Consensus Model With State-Dependent Connectivity
- On the mathematics of emergence
- Sparse dynamics for partial differential equations
- Stability Analysis of Flock and Mill Rings for Second Order Models in Swarming
- State transitions and the continuum limit for a 2D interacting, self-propelled particle system
- Universal algorithms for learning theory. I: Piecewise constant functions.
Cited in
(14)- Parameter calibration with stochastic gradient descent for interacting particle systems driven by neural networks
- Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories
- Tools to Characterize the Correlated Nature of Collective Dynamics
- 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
- The discovery of dynamics via linear multistep methods and deep learning: error estimation
- Nonparametric inference of interaction laws in systems of agents from trajectory data
- Learning theory for inferring interaction kernels in second-order interacting agent systems
- Data-Driven Model Selections of Second-Order Particle Dynamics via Integrating Gaussian Processes with Low-Dimensional Interacting Structures
- Learning particle swarming models from data with Gaussian processes
- Data-driven entropic spatially inhomogeneous evolutionary games
- Kernel-algorithms in frame-approximations
- Interacting particle systems on networks: joint inference of the network and the interaction kernel
- Approximation and error bounds for Kolmogorov-Arnold networks applications to dynamical system discovery via linear multistep methods
This page was built for publication: Data-driven discovery of emergent behaviors in collective dynamics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2127368)
