When can a neural operator replace a coarse solve? Architectural principles for two-level preconditioning
math.NA, cs.NA
Submitted: 2026-05-19
Updated: 2026-11-11
Code: https://github.com/HugoMelchers/neural-coarse-corrections
Terminology
Sources
- How Descriptive are GMRES Convergence Bounds?
- Learning Neural PDE Solvers with Convergence Guarantees
- Deep Learning-Enhanced Preconditioning for Efficient Conjugate Gradient Solvers in Large-Scale PDE Systems
- Fourier Neural Operator for Parametric Partial Differential Equations
- Neural Preconditioning Operator for Efficient PDE Solves
- Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter
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