Conference Time: 10th May 2024, 10:33:56am 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).
DFG-PP 2298: Theoretical Foundations of Deep Learning
Time:
Tuesday, 19/Mar/2024:
2:00pm - 4:00pm
Session Chair: Laura Thesing Session Chair: Gitta Kutyniok
Location: G22/013 Conference Room 013 in Building 22; size: 70
Presentations
2:00pm - 2:20pm Foundations of Supervised Deep Learning for Inverse Problems
A. Auras1 , M. Burger2,3 , S. Kabri 2 , M. Möller1
1 University of Siegen; 2 Helmholtz Imaging, Deutsches Elektronen-Synchrotron DESY; 3 Universität Hamburg
2:20pm - 2:40pm Combinatorial and implicit views on parameter optimization in neural networks
G. Montufar 1,2
1 University of California, Los Angeles, USA; 2 Max Planck Institute for Mathematics in the Sciences
2:40pm - 3:00pm Regularized, structure-preserving neural networks for the minimal entropy closure of the Boltzmann moment system
S. Schotthoefer 1 , P. Laiu1 , C. Hauck1 , M. Frank2
1 Oak Ridge National Laboratory, USA; 2 Karlsruhe Institute of Technology
3:00pm - 3:20pm Adaptive Step Sizes for Preconditioned Stochastic Gradient Descent
F. Köhne 1 , L. Kreis2 , A. Schiela1 , R. Herzog2
1 University of Bayreuth; 2 Heidelberg University
3:20pm - 3:40pm Non-vacuous PAC-Bayes bounds for Models under Adversarial Corruptions
W. Mustafa , P. Liznerski, A. Ledent, D. Wagner, P. Wang, M. Kloft
RPTU Kaiserslautern-Landau
3:40pm - 4:00pm Convergence results for gradient flow and gradient descent systems in artificial neural network training
A. Ahmadova
University of Duisburg-Essen
