Parameter calibration with stochastic gradient descent for interacting particle systems driven by neural networks

DOI10.1007/s00498-021-00309-8zbMath1489.93135arXiv2101.12657OpenAlexW3209403639MaRDI QIDQ2120450

Claudia Totzeck, Simone Goettlich

Publication date: 31 March 2022

Published in: MCSS. Mathematics of Control, Signals, and Systems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2101.12657

zbMATH Keywords

optimal controlneural networksparameter identificationdata analysis

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Optimal stochastic control (93E20)

Uses Software

• torchdiffeq

Cites Work

• Unnamed Item
• Unnamed Item
• Kinetic models of opinion formation
• Modeling of self-organized systems interacting with a few individuals: from microscopic to macroscopic dynamics
• Data-driven discovery of emergent behaviors in collective dynamics
• An anisotropic interaction model with collision avoidance
• Follow-the-leader models can be viewed as a numerical approximation to the Lighthill-Whitham-Richards model for traffic flow
• Multiscale modeling of pedestrian dynamics
• Parameter estimation of social forces in pedestrian dynamics models via a probabilistic method
• A consensus-based model for global optimization and its mean-field limit
• Inferring interaction rules from observations of evolutive systems I: The variational approach
• Particle, kinetic, and hydrodynamic models of swarming
• Optimization with PDE Constraints
• Stable architectures for deep neural networks
• Artificial Neural Networks for the Estimation of Pedestrian Interaction Forces
• Parameter Estimation for Macroscopic Pedestrian Dynamics Models from Microscopic Data
• Emergent Behavior in Flocks
• Mean-Field Optimal Control and Optimality Conditions in the Space of Probability Measures

This page was built for publication: Parameter calibration with stochastic gradient descent for interacting particle systems driven by neural networks