Multiscale LegONet: Learning Coefficient-Dependent Local Spaces for Composable Multiscale Finite Elements with Localized Error Bounds
math.NA, cs.NA
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/Yooki-YueqiWang/Ms-LegONet
Terminology
Sources
- Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers
- Locally Subspace-Informed Neural Operators for Efficient Multiscale PDE Solving
- Geometry-aware LegONet for PDE Learning on Arbitrary Domains
- LegONet: Plug-and-Play Structure-Preserving Neural Operator Blocks for Compositional PDE Learning
Related papers
- Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
- A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
- Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)
- Operator learning meets inverse problems: A probabilistic perspective
- Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
- Windowed thinning and query complexity for the bouncy particle and Zigzag samplers