9:45 - 10:00
10:00 - 10:45
Nonlinear model reduction using compositional polynomial networks
10:45 - 11:30
Some insights in operator learning for solving PDEs
11:30 - 11:45
11:45 - 12:30
Library-based nonlinear reduced modeling
12:30 - 14:00
14:00 - 14:45
14:45 - 15:30
Dropout Regularization Versus L²-Penalization in the Linear Model
15:30 - 16:00
16:00 - 16:45
Generative AI for the statistical computation of fluids
16:45 - 17:30
Registration in bounded domains for model reduction of parametric conservation laws
9:15 - 10:00
Analysis of gradient descent in neural networks for some PDEs
10:00 - 10:45
Improving the accuracy of classical methods with physics-informed basis functions
10:45 - 11:15
11:15 - 12:00
Structure preserving learning for ODE and PDE
12:00 - 13:30
13:30 - 14:15
Variationally correct residual regression for parametric PDEs
14:15 - 15:00
Opening the black-box: approximation and generalization properties of convolutional neural networks in surrogate modeling
15:00 - 15:45
Statistical Learning Theory for Neural Operators
15:45 - 17:30