Global and Local Reduced Models for Interacting, Heterogeneous Agents

Abstract

Large collections of coupled, heterogeneous agents can manifest complex dynamical behavior presenting difficulties for simulation and analysis. However, if the collective dynamics lie on a low-dimensional manifold then the original agent-based model may be approximated with a simplified surrogate model on and near the low-dimensional space where the dynamics live. This is typically accomplished by deriving coarse variables that summarize the collective dynamics, these may take the form of either a collection of scalars or continuous fields (e.g. densities), which are then used as part of a reduced model. Analytically identifying such simplified models is challenging and has traditionally been accomplished through the use of mean-field reductions or an Ott-Antonsen ansatz, but is often impossible. Here we present a data-driven coarse-graining methodology for discovering such reduced models. We consider two types of reduced models: globally-based models which use global information and predict dynamics using information from the whole ensemble, and locally-based models that use local information, that is, information from just a subset of agents close (close in heterogeneity space, not physical space) to an agent, to predict the dynamics of an agent. For both approaches we are able to learn laws governing the behavior of the reduced system on the low-dimensional manifold directly from time series of states from the agent-based system. A nontrivial conclusion is that the dynamics can be equally well reproduced by an all-to-all coupled as well as by a locally coupled model of the same agents.

arXiv comment16 pages, 14 figures

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Machine Learning for Fluid Mechanics
• Low Dimensional Behavior of Large Systems of Globally Coupled Oscillators
• Deep Neural Networks for Bot Detection
• COVID-ABS: An Agent-Based Model of COVID-19 Epidemic to Simulate Health and Economic Effects of Social Distancing Interventions
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Understanding the dynamics of biological and neural oscillator networks through exact mean-field reductions: a review
• Hyperviscosity, Galerkin truncation and bottlenecks in turbulence
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• Nonparametric inference of interaction laws in systems of agents from trajectory data
• Dynamics of noisy oscillator populations beyond the Ott-Antonsen ansatz
• Deep learning to discover and predict dynamics on an inertial manifold
• Coarse-scale PDEs from fine-scale observations via machine learning
• Learning differential equation models from stochastic agent-based model simulations
• Manifold learning for parameter reduction
• Linking Machine Learning with Multiscale Numerics: Data-Driven Discovery of Homogenized Equations
• An Emergent Space for Distributed Data with Hidden Internal Order through Manifold Learning
• Equation-Free Multiscale Computations in Social Networks: from Agent-based Modelling to Coarse-grained Stability and Bifurcation Analysis
• Dimension reduction in heterogeneous neural networks: generalized Polynomial Chaos (gPC) and ANalysis-Of-VAriance (ANOVA)
• The effects of within-neuron degree correlations in networks of spiking neurons
• Particles to Partial Differential Equations Parsimoniously

Cited by in corpus (2)

• Constructing coarse-scale bifurcation diagrams from spatio-temporal observations of microscopic simulations: A parsimonious machine learning approach
• Limits of Entrainment of Circadian Neuronal Networks