Reduced basis methods for time-dependent problems

JS Hesthaven, C Pagliantini, G Rozza - Acta Numerica, 2022 - cambridge.org
Numerical simulation of parametrized differential equations is of crucial importance in the
study of real-world phenomena in applied science and engineering. Computational methods …

Neural Galerkin schemes with active learning for high-dimensional evolution equations

J Bruna, B Peherstorfer, E Vanden-Eijnden - Journal of Computational …, 2024 - Elsevier
Deep neural networks have been shown to provide accurate function approximations in high
dimensions. However, fitting network parameters requires informative training data that are …

A robust second-order low-rank BUG integrator based on the midpoint rule

G Ceruti, L Einkemmer, J Kusch, C Lubich - BIT Numerical Mathematics, 2024 - Springer
Dynamical low-rank approximation has become a valuable tool to perform an on-the-fly
model order reduction for prohibitively large matrix differential equations. A core ingredient …

Symplectic model reduction of Hamiltonian systems using data-driven quadratic manifolds

H Sharma, H Mu, P Buchfink, R Geelen, S Glas… - Computer Methods in …, 2023 - Elsevier
This work presents two novel approaches for the symplectic model reduction of high-
dimensional Hamiltonian systems using data-driven quadratic manifolds. Classical …

Symplectic model reduction of Hamiltonian systems on nonlinear manifolds and approximation with weakly symplectic autoencoder

P Buchfink, S Glas, B Haasdonk - SIAM Journal on Scientific Computing, 2023 - SIAM
Classical model reduction techniques project the governing equations onto linear
subspaces of the high-dimensional state-space. For problems with slowly decaying …

Constructing custom thermodynamics using deep learning

X Chen, BW Soh, ZE Ooi, E Vissol-Gaudin… - Nature Computational …, 2024 - nature.com
One of the most exciting applications of artificial intelligence is automated scientific
discovery based on previously amassed data, coupled with restrictions provided by known …

A robust collision source method for rank adaptive dynamical low-rank approximation in radiation therapy

J Kusch, P Stammer - ESAIM: Mathematical Modelling and …, 2023 - esaim-m2an.org
Deterministic models for radiation transport describe the density of radiation particles
moving through a background material. In radiation therapy applications, the phase space of …

Nonlinear embeddings for conserving Hamiltonians and other quantities with Neural Galerkin schemes

P Schwerdtner, P Schulze, J Berman… - SIAM Journal on Scientific …, 2024 - SIAM
This work focuses on the conservation of quantities such as Hamiltonians, mass, and
momentum when solution fields of partial differential equations are approximated with …

Deep learning-based surrogate models for parametrized PDEs: Handling geometric variability through graph neural networks

NR Franco, S Fresca, F Tombari… - … Interdisciplinary Journal of …, 2023 - pubs.aip.org
Mesh-based simulations play a key role when modeling complex physical systems that, in
many disciplines across science and engineering, require the solution to parametrized time …

Model reduction techniques for parametrized nonlinear partial differential equations

NC Nguyen - Error Control, Adaptive Discretizations, and …, 2024 - books.google.com
2. Hyper-reduction methods 2.1 Parametrized integrals 2.2 Empirical quadrature methods
2.3 Empirical interpolation methods 2.4 Integral interpolation methods 3. First-order …