AI RESEARCH

SetONet: A Set-Based Operator Network for Solving PDEs with Variable-Input Sampling

arXiv CS.LG

ArXi:2505.04738v3 Announce Type: replace Most neural-operator surrogates for PDEs inherit from DeepONet-style formulations the requirement that the input function be sampled at a fixed, ordered set of sensors. This assumption limits applicability to problems with variable sensor layouts, missing data, point sources, and sample-based representations of densities.