arXiv:2606. 13827v1 Announce Type: cross Abstract: Markovian Whittle-Mat\'ern fields have been convergently approximated by discrete Gauss Markov Random Fields (GMRFs) with sparse precision matrices using a Finite Element approximation of the two-parameter family, \[ (\kappa^2 - \Delta)^{\alpha/2} u = \mathcal{W}, \;\; \kappa \in \mathbb{R}, \; \alpha \in \mathbb{N}.
arXiv:2606. 13827v2 Announce Type: replace-cross Abstract: Markovian Whittle-Mat\'ern fields have been convergently approximated by discrete Gauss Markov Random Fields (GMRFs) with sparse precision matrices using a Finite Element approximation of the two-parameter family, \[ (\kappa^2 - \Delta)^{\alpha/2} u = \mathcal{W}, \;\; \kappa \in \mathbb{R}, \; \alpha \in \mathbb{N}.
The paper introduces Spectrally Optimised Neural Discretisations (SpeND), a mesh‑free framework that learns discretisation weights from local stencil geometry on unstructured point clouds. By embedding discrete moment conditions into the network architecture, SpeND guarantees polynomial consistency and allows the weights to be optimised for spectral accuracy over a chosen wavenumber band, using an unsupervised Fourier‑mode loss. The resulting operators are PDE‑agnostic, perform well on Poisson, Burgers, and Navier–Stokes equations, and can reduce wall‑clock time by 3–20× compared to existing mesh‑free methods at the same accuracy.
The paper introduces PDE‑Residual‑Informed Kriging (PRIK), a Gaussian process framework that embeds global PDE residual information directly into its covariance structure via a PDE‑residual kernel. PRIK yields a posterior mean with minimal integrated squared PDE residual and offers statistical interpretations linking variance to residual energy. The authors prove quasi‑optimality and convergence rates, and demonstrate the method’s PDE‑solving capability through numerical experiments.
arXiv:2505. 04338v3 Announce Type: replace Abstract: We propose Riemannian Denoising Diffusion Probabilistic Models (RDDPMs) for learning distributions on submanifolds of Euclidean space that are level sets of functions, including most of the manifolds relevant to applications.
arXiv:2607.06644v2 Announce Type: replace Abstract: Determinantal point processes (DPPs) have recently emerged as a kernel-based alternative to standard independent sampling for constructing efficien...
arXiv:2607. 06644v1 Announce Type: cross Abstract: Determinantal point processes have recently emerged as a kernel-based alternative to standard independent sampling for constructing efficient minibatches, coresets, and other compact representations of large-scale datasets.
arXiv:2607. 23192v1 Announce Type: cross Abstract: We develop a data-driven approximation of the projected ambient connection Laplacian acting on differential forms over smooth Riemannian manifolds sampled by point clouds.
The paper introduces meshless Latent Dynamics Models (LDMs) for model order reduction of time‑dependent PDEs, using conditioning in Neural Fields to represent spatially continuous dynamics. It presents a unified mathematical framework, proves a Universal Approximation Theorem, and analyzes stability through Lipschitz bounds for different conditioning mechanisms, revealing an expressivity–stability trade‑off. Experiments on Burgers’ equation, Navier–Stokes flow, and linear advection demonstrate that meshless LDMs achieve comparable or better predictive accuracy than mesh‑based models while using only 2% of the parameters and maintaining near‑constant error across spatial discretizations.
EquiReg introduces an equivariance‑regularized diffusion framework that penalises sampling trajectories deviating from the data manifold, thereby improving posterior sampling for inverse problems. By formalising manifold‑preferential equivariant functions—naturally arising from data augmentation or inherent symmetries—EquiReg guides diffusion steps toward symmetry‑preserving regions of the solution space. The method shows consistent gains in both linear and nonlinear image restoration tasks and partial differential equation solving, especially under reduced sampling and measurement consistency steps, and is available as open‑source code.
arXiv:2606. 23867v1 Announce Type: new Abstract: The exact computation of the Normalized Maximum Likelihood (NML) codelength for regular non-smooth estimators (e.
Intrinsic methods fill the default toolbox for geometry processing on meshes. Intrinsic operators, in particular the Laplacian, underlie methods that require invariance to isometry and have hence been employed in many algorithms for shape analysis, learning, and editing.