MS04

Title: Deep learning meets inverse problems

Session 1

Name of the speaker	Title	University
Zhi Zhou	Identification of Conductivity in Elliptic Equations Using Deep Neural Networks	Hong Kong Polytechnic University
Guozhi Dong	Optimal Control of RELU Neural Network Informed Partial Differential Equations	Central South University
Junxiong Jia	Learning Prediction Policy of Prior Measures for Statistical Inverse Problems of PDEs	Xi’an Jiaotong University
Marco Inglesia	Ensemble Kalman Inversion for shape identification	University of Nottingham

Session 2

Name of the speaker	Title	University
Tim Jahn	Early Stopping of Untrained Neural Networks	University of Bonn
Sui Tang	A Robust Data-Driven Approach for Estimating Non-local Interaction Potential in Aggregation-Diffusion Equations From Noisy Data	University of California, Santa Barbara
Lingyun Qiu	Robust Full Waveform Inversion: A Source Wavelet Manipulation Perspective	Tsinghua University
Tianhao Hu	Solving Elliptic Problems With Singular Solutions Using Splitting Technique	The Chinese University of Hong Kong

Session 3

Name of the speaker	Title	University
Ye Zhang	Estimating Adsorption Isotherm Parameters in Chromatography via a Virtual Injection Promoting Double Feed-Forward Neural Network	SMBU
Yuling Jiao	Inversion of Drift in SDE with Deep Learning	Wuhan University
Fengru Wang	Deep Ritz Method for Optimization With Elliptical Constrains in High Dimensional Space	The Chinese University of Hong Kong

Session 4

Name of the speaker	Title	University
Ruchi Guo	Transformer Meets Boundary Value Inverse Problems	The Chinese University of Hong Kong
Wenbin Li	Convex Neural Networks for Inverse Problems in Imaging	Harbin Institute of Technology
Xiliang Lu	Current Density Impedance Imaging with PINNs	Wuhan University
Dong Wang	Efficient Algorithms for Partition Problems	The Chinese University of Hong Kong, Shenzhen