Conference Time: 10th May 2024, 03:06:53am CEST
Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
MS4: Kernel Methods in Data Analysis and Computational Science
Time:
Tuesday, 19/Mar/2024:
2:00pm - 4:00pm
Session Chair: Jochen Garcke Session Chair: André Uschmajew
Location: G22/112 Conference Room 112 in Building 22; size: 40
Presentations
2:00pm - 2:30pm Gaussian Process Surrogate for Bayesian Parameter Estimation Involving Incompressible Fluids
H. Wendland 1 , I. Sloan2 , Q. T. Le Gia2
1 University of Bayreuth; 2 University of New South Wales, Australia
2:30pm - 3:00pm How many neurons do we need? A refined analysis for shallow networks trained with gradient descent
N. Mücke , M. Nguyen
TU Braunschweig
3:00pm - 3:30pm Some results on the NTK spectrum and spectral bias of neural networks in the kernel regime
G. Montufar 1,2
1 University of California, Los Angeles, USA; 2 Max Planck Institute for Mathematics in the Sciences, Leipzig
3:30pm - 4:00pm Kernel Methods for Koopman-based Modeling
F. Nüske
Max Planck Institute for Dynamics of Complex Technical Systems, Magdeburg
