McMg: A Learned Phase-Space Multi-channel Multigrid Preconditioner for Helmholtz Equation

• URL: http://arxiv.org/abs/2606.30495v2
• Date: Thu, 02 Jul 2026 08:05:47 GMT
• Title: McMg: A Learned Phase-Space Multi-channel Multigrid Preconditioner for Helmholtz Equation
• Abstract summary: Multi-channel Multigrid is a learned phase-space multigrid preconditioner for heterogeneous Helmholtz equations.<n>It maps residuals to corrections within an iterative framework.<n>It requires substantially fewer iterations and less wall-clock time than strong classical baselines.
• Score: 7.198826777148334
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Solving heterogeneous Helmholtz equations at high wavenumbers remains challenging because the discretized operator is indefinite, pollution degrades phase accuracy, and scalar coarse-grid correction can discard the local phase and propagation-direction information carried by oscillatory errors. We propose Multi-channel Multigrid (McMg), a learned phase-space multigrid preconditioner for heterogeneous Helmholtz equations. Rather than predicting the solution directly, McMg maps residuals to corrections within an iterative framework. Its central idea is to coarsen physical space while retaining unresolved local wave information in the channel dimension: each coarse node carries a learned packet of amplitude, phase, direction, and scattering coefficients rather than a single scalar unknown. The architecture combines linear multi-channel transfer operators with locally adaptive stencils, neural PDE operators, and medium-dependent smoothers whose coefficients are generated from the wave speed. For a fixed medium, the V-cycle is linear in the residual; nonlinear physical features are computed once in a setup phase and cached, so each online iteration reduces to convolutions with fixed coefficients. We further study generalization across scales. Models trained on small domains transfer directly to larger domains and higher effective wavenumbers, and a Layer-by-Layer Progressive Finetuning (LLPF) strategy improves large-domain scalability by adding new coarse levels while finetuning only the newly introduced parameters. Numerical experiments on high-frequency, high-contrast, and large-scale three-dimensional problems demonstrate that McMg requires substantially fewer iterations and less wall-clock time than strong classical baselines, while consistently outperforming existing neural preconditioners.

Related papers

• Adaptive Hybrid Subspace Levenberg Marquardt Algorithm with Adequacy Monitor for Large Scale Least Squares Problems [0.0]
  The Levenberg-Marquardt (LM) algorithm is the most widely used method for solving nonlinear least-squares problems.<n>We propose an adaptive hybrid subspace Levenberg-Marquardt (HSLM) algorithm that constructs a low-dimensional subspace.<n>HSLM achieves convergence behavior comparable to classical and Krylov subspace LM (KSLM) while substantially reducing per-itarity computational cost.
  arXiv  Detail & Related papers  (2026-08-26T08:33:33Z)
• Operator-Informed Gaussian Processes for Complex Helmholtz Wavefields: From Synthetic Benchmarks to In Vivo Brain Elastography [0.02780623255172367]
  We extend operator-informed GP regression to complex-valued Helmholtz problems.<n>The construction admits a family of priors, from a proper diagonal prior to coregionalized and multiscale variants.<n>Calibrated uncertainty emerges as the central next step for probabilistic wavefield inference in dissipative media.
  arXiv  Detail & Related papers  (2026-07-15T16:21:50Z)
• Learning to Solve Generative ODEs Beyond the Linear Span [50.13853710831612]
  We propose SpanLift, a lightweight neural solver that augments scalar-coefficient updates with a spatial residual operator.<n>Across pixel-space diffusion, latent flow matching, and precipitation nowcasting, SpanLift achieves state-of-the-art few-step sampling.
  arXiv  Detail & Related papers  (2026-06-07T15:22:13Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• WLNO: Wavelet-Laplace Neural Operator for Solving Partial Differential Equations [0.6008132390640294]
  Wavelet-Laplace Neural Operator fuses Haar wavelet multi-scale spatial decomposition with the Laplace-domain pole-residue formulation of the Laplace Neural Operator (LNO)<n>LNO captures transient and steady-state dynamics through learnable system poles and residues, but lacks an explicit mechanism for extracting localized multi-scale features inherent in complex PDE solutions.<n> WLNO addresses this by augmenting the LNO core with a parallel single-level Haar discrete wavelet transform (DWT) branch that decomposes the lifted feature map into four frequency subbands.<n> WLNO consistently outperforms LNO on
  arXiv  Detail & Related papers  (2026-05-23T16:58:37Z)
• DInf-Grid: A Neural Differential Equation Solver with Differentiable Feature Grids [73.28614344779076]
  We present a differentiable grid-based representation for efficiently solving differential equations (DEs)<n>Our results demonstrate a 5-20x speed-up over coordinate-based methods, solving differential equations in seconds or minutes while maintaining comparable accuracy and compactness.
  arXiv  Detail & Related papers  (2026-01-15T18:59:57Z)
• Equivariant U-Shaped Neural Operators for the Cahn-Hilliard Phase-Field Model [4.79907962230318]
  We show that an equivariant U-shaped neural operator (E-UNO) can learn the evolution of the phase-field variable from short histories of past dynamics.<n>By encoding symmetry and scale hierarchy, the model generalizes better, requires less training data, and yields physically consistent dynamics.
  arXiv  Detail & Related papers  (2025-09-01T09:25:31Z)
• Gradient Flow Based Phase-Field Modeling Using Separable Neural Networks [1.2277343096128712]
  We propose a separable neural network-based approximation of the phase field in a minimizing movement scheme to solve a gradient flow problem. The proposed method outperforms the state-of-the-art machine learning methods for phase separation problems.
  arXiv  Detail & Related papers  (2024-05-09T21:53:27Z)
• An N-Point Linear Solver for Line and Motion Estimation with Event Cameras [45.67822962085412]
  Event cameras respond primarily to edges--formed by strong gradients--that are well-suited for motion estimation. Recent work has shown that events generated by single lines satisfy a novel constraint which describes a manifold in space-time volume. We show that, with suitable line parametrization, this system of constraints is actually linear in the unknowns.
  arXiv  Detail & Related papers  (2024-04-01T00:47:02Z)
• Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction [49.66486092259376]
  The mean-field Langevin dynamics (MFLD) is a nonlinear generalization of the Langevin dynamics that incorporates a distribution-dependent drift. Recent works have shown that MFLD globally minimizes an entropy-regularized convex functional in the space of measures. We provide a framework to prove a uniform-in-time propagation of chaos for MFLD that takes into account the errors due to finite-particle approximation, time-discretization, and gradient approximation.
  arXiv  Detail & Related papers  (2023-06-12T16:28:11Z)
• Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems [64.29491112653905]
  We propose a novel and efficient diffusion sampling strategy that synergistically combines the diffusion sampling and Krylov subspace methods. Specifically, we prove that if tangent space at a denoised sample by Tweedie's formula forms a Krylov subspace, then the CG with the denoised data ensures the data consistency update to remain in the tangent space. Our proposed method achieves more than 80 times faster inference time than the previous state-of-the-art method.
  arXiv  Detail & Related papers  (2023-03-10T07:42:49Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)

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.