Zero coordinate shift: Whetted automatic differentiation for physics-informed operator learning

Kuangdai Leng, Mallikarjun Shankar, Jeyan Thiyagalingam

Abstract: Highlights•We present a novel algorithm to conduct automatic differentiation w.r.t. coordinates for physics-informed operator learning.•Our algorithm can reduce GPU memory and wall time for training physics-informed DeepONets by an order of magnitude.•Our algorithm neither affects training results nor imposes any restrictions on data, physics (PDE) or network architecture.