NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces

• URL: http://arxiv.org/abs/2605.07828v2
• Date: Mon, 11 May 2026 14:21:12 GMT
• Title: NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces
• Abstract summary: We introduce Neural Subspace Proper Orthogonal Decomposition (NSPOD), a multigrid-like deep operator network-based preconditioner.<n>NSPOD can dramatically reduce the number of iterations needed for convergence in Krylov-based linear iterative solvers.<n>We demonstrate its efficiency via numerical experiments on a linearized version of solid mechanics PDEs applied to unstructured domains.
• Score: 5.532017361572708
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Convolutional Symmetric AutoEncoders: enhancing latent stability via differential geometry [0.0]
  This study builds upon works by arXiv:2307.15288v2 and arXiv:2506.11641v1 by extending representation consistency for convolutional layers.<n>We introduce a novel class of symmetric Convolutional AutoEncoders (CAEs) designed to embody the primary properties of manifold parametrization mappings.
  arXiv  Detail & Related papers  (2026-07-01T09:16:37Z)
• Symplectic H2 Model Reduction for High-Dimensional Linear Quantum Systems [3.7887687619674413]
  A symplectic Petrov-Galerkin framework is presented, in which reduced-order models automatically satisfy the PR identities by construction.<n>A symplectic variant of the iterative rational Krylov algorithm is developed and referred to as Quantum IRKA (Q-IRKA)<n>Results show that Q-IRKA is effective for large-scale linear quantum systems.
  arXiv  Detail & Related papers  (2026-05-08T02:38:57Z)
• BEACONS: Bounded-Error, Algebraically-Composable Neural Solvers for Partial Differential Equations [0.0]
  We show how it is possible to circumvent limitations by constructing formally-verified neural network solvers for PDEs.<n>We show how it is possible to construct rigorous extrapolatory bounds on the worst-case Linf errors of shallow neural network approximations.<n>The resulting framework, called BEACONS, comprises both an automatic code-proving for the neural solvers themselves, as well as a bespoke automated theorem-generator system for producing machine-checkable certificates of correctness.
  arXiv  Detail & Related papers  (2026-02-16T15:49:19Z)
• NeuraLSP: An Efficient and Rigorous Neural Left Singular Subspace Preconditioner for Conjugate Gradient Methods [49.84495044725856]
  NeuraLSP is a novel neural preconditioner combined with a novel loss metric.<n>Our method exhibits both theoretical guarantees and empirical robustness to rank inflation, up to a 53% speedup.
  arXiv  Detail & Related papers  (2026-01-28T02:15:16Z)
• Hybrid Iterative Solvers with Geometry-Aware Neural Preconditioners for Parametric PDEs [5.532017361572708]
  We introduce Geo-DeepONet, a geometry-aware deep operator network that incorporates domain information extracted from finite element discretizations.<n>We develop a class of geometry-aware hybrid preconditioned iterative solvers by coupling Geo-DeepONet with traditional methods such as relaxation schemes and Krylov subspace algorithms.
  arXiv  Detail & Related papers  (2025-12-16T17:06:10Z)
• Data-Driven Adaptive Gradient Recovery for Unstructured Finite Volume Computations [0.0]
  We present a novel data-driven approach for enhancing gradient reconstruction in unstructured finite volume methods for hyperbolic conservation laws.<n>Our approach extends previous structured-grid methodologies to unstructured meshes through a modified DeepONet architecture.<n>The proposed algorithm is faster and more accurate than the traditional second-order finite volume solver.
  arXiv  Detail & Related papers  (2025-07-22T13:23:57Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation [52.73824786627612]
  This paper establishes new convergence results for textitgeodesic strongly monotone games.<n>Our key result shows that RGD attains last-iterate linear convergence in a textitgeometry-agnostic fashion.<n>Overall, this paper presents the first geometry-agnostic last-iterate convergence analysis for games beyond the Euclidean settings.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• Neural Basis Functions for Accelerating Solutions to High Mach Euler Equations [63.8376359764052]
  We propose an approach to solving partial differential equations (PDEs) using a set of neural networks. We regress a set of neural networks onto a reduced order Proper Orthogonal Decomposition (POD) basis. These networks are then used in combination with a branch network that ingests the parameters of the prescribed PDE to compute a reduced order approximation to the PDE.
  arXiv  Detail & Related papers  (2022-08-02T18:27:13Z)
• Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization [98.0595480384208]
  We propose a generalization extraient spaces which converges to a stationary point. The algorithm applies not only to general $p$-normed spaces, but also to general $p$-dimensional vector spaces.
  arXiv  Detail & Related papers  (2020-10-31T21:35:42Z)
• Multipole Graph Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data. We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
  arXiv  Detail & Related papers  (2020-06-16T21:56:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.