Neural Inverse Operators for Solving PDE Inverse Problems
원문 초록
A large class of inverse problems for PDEs are only well-defined as mappings from operators to functions. Existing operator learning frameworks map functions to functions and need to be modified to learn inverse maps from data. We propose a novel architecture termed Neural Inverse Operators (NIOs) to solve these PDE inverse problems. Motivated by the underlying mathematical structure, NIO is based on a suitable composition of DeepONets and FNOs to approximate mappings from operators to functions. A variety of experiments are presented to demonstrate that NIOs significantly outperform baselines and solve PDE inverse problems robustly, accurately and are several orders of magnitude faster than existing direct and PDE-constrained optimization methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Mesh-Informed Neural Operator : A Transformer Generative Approach
Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning
Learning Where to Learn: Training Distribution Selection for Provable OOD Performance
Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems
Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary Domains
Operator Learning for Schrödinger Equation: Unitarity, Error Bounds, and Time Generalization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.