Neural Operators for Nonlinear Functionals on RKHS
By leveraging interpolating orthogonal projections in RKHSs, this work uses finitely many point evaluations in place of integration-based basis function expansions to lead to a simpler and more flexible neural-network architecture that remains applicable even when the data domain or the underlying kernel is not explici...
Tiancong Zhou, Namjoon Suh, Guang Cheng et al.
· 6 citations
· ⚡1