2 papers
cs.LG2025
A Control Perspective on Training PINNs
Matthieu Barreau, Haoming Shen
We investigate the training of Physics-Informed Neural Networks (PINNs) from a control-theoretic perspective. Using gradient descent with resampling, we interpret the training dyna…
math.OC2022
Wasserstein Two-Sided Chance Constraints with An Application to Optimal Power Flow
Haoming Shen, Ruiwei Jiang
As a natural approach to modeling system safety conditions, chance constraint (CC) seeks to satisfy a set of uncertain inequalities individually or jointly with high probability. A…