Schedule
Monday June 19 (Venue: Sheraton Baltimore North Hotel)
Chair: Mingchao Cai
8:20 - 8:30. Opening Ceremony. Drs Willie May & Asamoah Nkwanta
10:10 - 10:55
Newton's method for solving PDEs with neural network discretization and applications. [slides]
Lunch Break 12:00 - 2:00
3:40 - 4:25
Efficient Numerical Methods for Weak Solutions of Partial Differential Equations [slides]
Tuesday June 20
Chair: Haizhao Yang
Lunch Break 12:00 - 2:00
4:30 - 4:40
Deep operator learning lessens the curse of dimensionality for PDEs
Wednesday June 21
Chair: Yue Yu
Lunch Break 12:00 - 2:00
Thursday June 22
Chair: Jonathan Siegel
11:00 - 11:45
GPT-PINN: Generative Pre-Trained Physics-Informed Neural Networks toward non-intrusive Meta-learning of parametric PDEs. [slides]
Lunch Break 12:00 - 2:00
2:00 - 2:45
On the Representation, Approximation, and Interpolation Power of Neural Networks. [slides]
2:45 - 3:30
A New Practical Framework for the Stability Analysis of Perturbed Saddle-point Problems and Applications. [slides]
3:40 - 4:30
Panel discussions
Friday June 23
Chair: Jiequn Han
11:00 - 11:45
Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks. [slides]
Lunch Break 12:00 - 2:00
2:00 - 3:00
Variational formulations of the strong form for forward and inverse problems - applications to neural nets and isogeometric analysis. [slides]
3:20 - 4:05
A Neural Network Warm-Start Approach for the Inverse Acoustic Obstacle Scattering Problem. [slides]