Schedule

Principal Lecture. Jinchao Xu. KAUST and Penn State University  [slides]

Wenrui Hao. Pennsylvania State University.

Newton's method for solving PDEs with neural network discretization and applications.  [slides]

Haizhao Yang.  University of Maryland College Park. 

Finite Expression Method: A Symbolic Approach for Scientific Machine Learning  [slides]

Principal Lecture. Jinchao Xu. KAUST and Penn State University.

Chunmei Wang. University of Florida. 

Efficient Numerical Methods for Weak Solutions of Partial Differential Equations  [slides]

Principal Lecture. Jinchao Xu. KAUST and Penn State University.  [slides]

Yue Yu. Lehigh University.

Learning Implicit PDE Solution Operators for Complex Physical System Modeling.  [slides]

Juncai He. KAUST. 

MgNet: Algorithms, Theories and Applications in Numerical PDEs.  [slides]

Principal Lecture. Jinchao Xu. KAUST and Penn State University. 

Bao Wang. University of Utah. 

The Effects of Activation Functions on the Over-smoothing Issue of Graph Convolutional Networks. [slides]

Ke Chen. University of Maryland College Park. 

Deep operator learning lessens the curse of dimensionality for PDEs

Qijia Zhai. Sichuan University. 

A New Reduced Order Method for Parabolic Equation Based on Single-Eigenvalue Acceleration

Yi Zong. Tsinghua University. 

Fast and Scalable Structured Multigrid Preconditioner with Half-Precision Acceleration

Principal Lecture. Jinchao Xu. KAUST and Penn State University.  [slides]

Shuhao Cao. University of Missouri-Kansas City. 

Structure-Conforming Operator Learning. [slides]

Yiping Lu. Stanford University. 

Understanding the Power and Limit of Scientific Machine Learning.  [slides]

Principal Lecture. Jinchao Xu. KAUST and Penn State University. 

Lu Lu. University of Pennsylvania. 

Deep neural operators with reliable extrapolation for multiphysics, multiscale & multifidelity problems.  [slides]

Yi Xiao. Tsinghua University. 

Deep Learning for Data Assimilation in Numerical Weather Prediction

Jialong Li. Texas State University. 

Explore training algorithm for multinomial logistic regression

Jianqi Zhao. China University of Petroleum-Beijing, China. 

SFLU: Synchronization-Free Sparse LU Factorization for Fast Circuit Simulation on GPUs

Xu Fu. China University of Petroleum-Beijing, China. 

PanguLU: A Scalable Regular Two-Dimensional Block-Cyclic Sparse Direct Solver on Distributed Heterogeneous Systems

Principal Lecture. Jinchao Xu. KAUST and Penn State University.  [slides]

Hongkai Zhao. Duke University. 

Numerical analysis 101 for neural networks.  [slides]

Yanlai Chen. University of Massachusetts Dartmouth. 

GPT-PINN: Generative Pre-Trained Physics-Informed Neural Networks toward non-intrusive Meta-learning of parametric PDEs.  [slides]

Jonathan Siegel. Texas A&M. 

On the Representation, Approximation, and Interpolation Power of Neural Networks.  [slides]

Qingguo Hong.  The Pennsylvania State University

A New Practical Framework for the Stability Analysis of Perturbed Saddle-point Problems and Applications.  [slides]

Panel discussions

Zezheng Song. University of Maryland College Park. 

A Finite Expression Method for Solving High-Dimensional Committor Problems

Xiaofeng Xu. KAUST. 

A neuron-wise subspace correction method for the finite neuron method

Bing Han. Morgan State University. 

Numerical Simulation of Respiratory Airflow in Central Airways with Elastic Boundary Conditions

Principal Lecture. Jinchao Xu. KAUST and Penn State University.  [slides]

Jonathan Siegel. Texas A&M. 

The Approximation Theory of Shallow Neural Networks

Penghang Yin. State University of New York at Albany

Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks.  [slides]

Kent-Andre Mardal. University of Oslo. 

Variational formulations of the strong form for forward and inverse problems - applications to neural nets and isogeometric analysis. [slides]

Jiequn Han. Flatiron Institute 

A Neural Network Warm-Start Approach for the Inverse Acoustic Obstacle Scattering Problem.  [slides]