Born-Series-Inspired Residual Metric for Learning-based Preconditioners
This addresses the problem of inefficient iterative solvers for ill-conditioned PDE systems in computational physics and engineering, though it appears incremental as it builds on existing preconditioning concepts with neural enhancements.
The paper tackles the problem of learning-based preconditioners for PDEs being overly sensitive to near-resonant spectral components due to inappropriate residual metrics, particularly for indefinite operators like the Helmholtz equation. The result is a Neural Preconditioned Born Series (NPBS) method with a metric-matched loss that demonstrates effectiveness on heterogeneous Helmholtz problems and yields substantial iteration reductions for other PDE classes.
Loss functions for learning-based PDE preconditioners implicitly choose a \emph{metric} in which residuals are matched, yet most approaches still optimize an unpreconditioned Euclidean residual norm. For indefinite operators such as the high-frequency Helmholtz equation, this default metric can make both learning and iterative correction overly sensitive to near-resonant spectral components, while classical preconditioning succeeds precisely by reshaping the residual geometry. We show that the Born Series and shifted-Laplacian left preconditioning are linked by the identity $ I-G_ηV_η= G_ηA = L_η^{-1}A, $ which turns the reference Green operator $G_η$ into a natural Riesz-map residual metric $ R_η= G_η^\ast G_η$ and suggests measuring the physical residual via $ \|r\|_{R_η}=\|G_ηr\|_2. $ Building on this viewpoint, we propose a \emph{Neural Preconditioned Born Series} (NPBS) iteration that replaces the scalar CBS relaxation with a residual-driven neural operator, together with a metric-matched Born-series-inspired loss $\mathcal{L}_{\mathrm{bs}}^{R_η}$. The framework is architecture-agnostic and supports fast $\mathcal{O}(N\log N)$ evaluation via FFT/DST/DCT. Numerical experiments on heterogeneous Helmholtz problems demonstrate the effectiveness of our method, and its advantage becomes more pronounced as the systems grow more ill-conditioned; we then extend the framework to other PDE classes, including convection--diffusion--reaction equations and linearized Newton systems for nonlinear PDEs, where it also yields substantial iteration reductions.