Philip E. Paré

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2025

Learning Passive Continuous-Time Dynamics with Multistep Port-Hamiltonian Gaussian Processes

Chi Ho Leung, Philip E. ParÃ©

We propose the multistep port-Hamiltonian Gaussian process (MS-PHS GP) to learn physically consistent continuous-time dynamics and a posterior over the Hamiltonian from noisy, irre…

cs.LG2025

A Physics-Informed Neural Networks-Based Model Predictive Control Framework for $S I R$ Epidemics

This work introduces a physics-informed neural networks (PINNs)-based model predictive control (MPC) framework for susceptible-infected-recovered ( $S I R$ ) spreading models. Existing…

Learning Passive Continuous-Time Dynamics with Multistep Port-Hamiltonian Gaussian Processes

A Physics-Informed Neural Networks-Based Model Predictive Control Framework for SIR Epidemics

A Physics-Informed Neural Networks-Based Model Predictive Control Framework for $S I R$ Epidemics