Adversarial Autoencoders in Operator Learning

Abstract

DeepONets and Koopman autoencoders are two prevalent neural operator architectures. These architectures are autoencoders. An adversarial addition to an autoencoder have improved performance of autoencoders in various areas of machine learning. In this paper, the use an adversarial addition for these two neural operator architectures is studied.

arXiv admin note: substantial text overlap with arXiv:2412.06686, arXiv:2412.04578