3 papers
math.NA2024
Deep orthogonal decomposition: a continuously adaptive data-driven approach to model order reduction
Nicola Rares Franco, Andrea Manzoni, Paolo Zunino +1
We develop a novel deep learning technique, termed Deep Orthogonal Decomposition (DOD), for dimensionality reduction and reduced order modeling of parameter dependent partial diffe…
cs.LG2024
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…
cs.LG2024
Recurrent Deep Kernel Learning of Dynamical Systems
Nicolò Botteghi, Paolo Motta, Andrea Manzoni +2
Digital twins require computationally-efficient reduced-order models (ROMs) that can accurately describe complex dynamics of physical assets. However, constructing ROMs from noisy…