Learning effective models from network dynamics data with multiple initial conditions using weak form SINDy
Social systems consist of networks of individuals who influence one another through social interactions. Studying how processes evolve on these networks can help us better understand patterns of social behavior. We study a system that couples online and offline social activity and investigate how to learn effective models directly from data using Weak Form Sparse Identification of Nonlinear Dynamics (WSINDy), a method for discovering governing equations. We assess learning performance using data generated by a mean-field approximation model of a stochastic interaction process on networks and test how accurately the system can be recovered under different noise levels. Our results show that using more trajectories improves accuracy when noise is high, but only a small number of additional trajectories is needed to gain most of the benefit, with little improvement beyond that. We also learn effective ODE models from averaged stochastic data on networks. When traditional mean-field approximations fail, identifying continuum ODEs directly from stochastic processes yields efficient models that better match the data and provide deeper insight into the underlying dynamics.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Receding Horizon Iterative Learning Control for Continuously Operated Systems
This paper presents an iterative learning control (ILC) scheme for continuously operated repetitive systems for which no initial condition reset exists. To accomplish this, we develop a lifted system representation that …
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
Despite the widespread practical success of deep learning methods, our theoretical understanding of the dynamics of learning in deep neural networks remains quite sparse. We attempt to bridge the gap between the theory a…
Unsupervised Pre-trainingLarge-N dynamics of the spiked tensor model with random initial conditions
In these notes, we develop a path integral approach for the partial differential equations with random initial conditions. Then, we apply it to the dynamics of the spiked tensor model and show that the large-$N$ saddle p…
MPINeuralODE: Multiple-Initial-Condition Physics-Informed Neural ODEs for Globally Consistent Dynamical System Learning
Neural ordinary differential equations (Neural ODEs) often fit training trajectories while generalizing poorly to unseen initial conditions and long horizons. We propose MPINeuralODE, which combines a soft physics-inform…
Learning and discovering multiple solutions using physics-informed neural networks with random initialization and deep ensemble
We explore the capability of physics-informed neural networks (PINNs) to discover multiple solutions. Many real-world phenomena governed by nonlinear differential equations (DEs), such as fluid flow, exhibit multiple sol…
Uncertainty Quantification