2000 character limit reached
Loss Terms and Operator Forms of Koopman Autoencoders
Published 5 Dec 2024 in cs.LG and physics.comp-ph | (2412.04578v1)
Abstract: Koopman autoencoders are a prevalent architecture in operator learning. But, the loss functions and the form of the operator vary significantly in the literature. This paper presents a fair and systemic study of these options. Furthermore, it introduces novel loss terms.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.