Neural-POD: A Plug-and-Play Neural Operator Framework for Infinite-Dimensional Functional Nonlinear Proper Orthogonal Decomposition
Published in arXiv preprint, 2026
Neural-POD generalizes proper orthogonal decomposition to the infinite-dimensional, nonlinear, functional setting by parameterizing modes as neural operators. The framework is plug-and-play: it slots into existing reduced-order modeling pipelines and recovers expressive, data-driven manifolds for high-dimensional PDE solutions while remaining stable on out-of-distribution flow regimes.
Recommended citation: Mou, C., Lu, B., & Lin, G. (2026). "Neural-POD: A Plug-and-Play Neural Operator Framework for Infinite-Dimensional Functional Nonlinear Proper Orthogonal Decomposition." arXiv:2602.15632.
Download Paper