AI RESEARCH
Revisiting Neural Processes via Fourier Transform and Volterra Series
arXiv CS.LG
•
ArXi:2606.01172v1 Announce Type: new Modeling unknown latent functions from finite, irregularly sampled measurements is a recurring challenge across science and engineering. Neural processes (NPs), a family of probabilistic functional models, are promising solutions -- especially when endowed with domain-specific symmetries like translation equivariance, which improve sample efficiency and generalization.