5 papers
Reliability of Probabilistic Emulation of Physical Systems
Sam F. Greenbury, Radka Jersakova, Paolo Conti +4
Two dominant approaches have emerged for generating probabilistic forecasts of physical systems: generative models, such as diffusion or flow matching; and ensembles of determinist…
Progressive multi-fidelity learning with neural networks for physical system predictions
Paolo Conti, Mengwu Guo, Attilio Frangi +1
Highly accurate datasets from numerical or physical experiments are often expensive and time-consuming to acquire, posing a significant challenge for applications that require prec…
Multi-Fidelity Delayed Acceptance: hierarchical MCMC sampling for Bayesian inverse problems combining multiple solvers through deep neural networks
Filippo Zacchei, Paolo Conti, Attilio Alberto Frangi +1
Inverse uncertainty quantification (UQ) tasks such as parameter estimation are computationally demanding whenever dealing with physics-based models, and typically require repeated…
VENI, VINDy, VICI: a generative reduced-order modeling framework with uncertainty quantification
Paolo Conti, Jonas Kneifl, Andrea Manzoni +4
The simulation of many complex phenomena in engineering and science requires solving expensive, high-dimensional systems of partial differential equations (PDEs). To circumvent thi…
Online learning in bifurcating dynamic systems via SINDy and Kalman filtering
Luca Rosafalco, Paolo Conti, Andrea Manzoni +2
We propose the use of the Extended Kalman Filter (EKF) for online data assimilation and update of a dynamic model, preliminary identified through the Sparse Identification of Nonli…