NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces
math.NA, cs.LG, cs.NA
Submitted: 2026-05-08
Updated: 2026-05-11
Comments: 17 pages, 9 figures, 3 tables
Journal ref: Computer Methods in Applied Mechanics and Engineering. 464 (2027) 119488
DOI: 10.1016/j.cma.2026.119488
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: The convergence of Krylov-based linear iterative solvers applied to parametric partial differential equations (PDEs) is often highly sensitive to the domain, its discretization…
Terminology
Abstract
The convergence of Krylov-based linear iterative solvers applied to parametric partial differential equations (PDEs) is often highly sensitive to the domain, its discretization, the location/values of the applied Dirichlet/Neumann boundary conditions, body forces and material properties, among others. We have previously introduced hybridization of classical linear iterative solvers with neural operators for specific geometries, but they tend to not perform well on geometries not previously seen during training. We partially addressed this challenge by introducing the deep operator network Geo-DeepONet and hybridizing it with Krylov-based iterative linear solvers, which, despite learning effectively across arbitrary unstructured meshes without requiring retraining, led to only modest reductions in iterations compared to state-of-the-art preconditioners. In this study we introduce Neural Subspace Proper Orthogonal Decomposition (NSPOD), a multigrid-like deep operator network-based preconditioner which can dramatically reduce the number of iterations needed for convergence in Krylov-based linear iterative solvers, even when compared to state-of-the-art methods such as algebraic multigrid preconditioners. We demonstrate its efficiency via numerical experiments on a linearized version of solid mechanics PDEs applied to unstructured domains obtained from complex CAD geometries. We expect that the findings in this study lead to more efficient hybrid preconditioners that can match, or possibly even surpass, the convergence properties of the current gold standard preconditioning methods for solid mechanics PDEs.
Sources
- Hybrid Iterative Solvers with Geometry-Aware Neural Preconditioners for Parametric PDEs
- Automatic discovery of optimal meta-solvers for time-dependent nonlinear PDEs
- Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
- A Survey on Oversmoothing in Graph Neural Networks
- Revisiting Over-smoothing in Deep GCNs
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