{
 "artifacts": null,
 "category": "geometry",
 "description": "Replace isotropic neighbor aggregation in a graph or point-cloud neural network with a local anisotropic diffusion operator determined by empirical first and second moments of each neighborhood. Subtract the first-moment drift before aggregation, and use the normalized second-moment tensor to mix feature derivatives along the locally supported directions.",
 "formulas_latex": [
  "$$A_h f(x)=\\frac{1}{h^2}\\fint_{B(x,h)}\\bigl(f(q)-f(x)\\bigr)\\,d\\mu(q).$$",
  "$$\\fint_{B(x,h)}f(q)\\,dq-f(x)=\\frac{h^2}{2(n+2)}\\Delta f(x)+o(h^2).$$",
  "$$A_h f(x)\\approx \\frac{1}{h}\\nabla f(x)^T m_h(x)+\\frac{1}{2}\\,\\nabla^2 f(x):C_h(x),\\quad m_h(x)=\\fint_{B(x,h)}\\frac{\\xi(q)}{h}\\,d\\mu(q),\\quad C_h(x)=\\fint_{B(x,h)}\\frac{\\xi(q)\\xi(q)^T}{h^2}\\,d\\mu(q).$$",
  "$$\\widetilde{\\mathcal{D}}_i H_i=\\frac{1}{2}\\sum_{a,b}(C_i)_{ab}\\,\\delta_a\\delta_b H_i,\\qquad \\delta_a H_i=\\sum_{j\\in\\mathcal{N}(i)}w_{ij}(\\xi_{ij,a}-\\bar\\xi_{i,a})H_j.$$"
 ],
 "id": 3076,
 "implementation": "Integrate this at the neighbor-aggregation stage of a point-cloud, graph, or geometric transformer block. For every node i, construct a k-nearest-neighbor set N(i), local coordinates \\xi_ij=(x_j-x_i)/r_i in a fixed or learned local frame, and normalized positive weights w_ij proportional to exp(-||\\xi_ij||^2/\\tau), with sum_j w_ij=1. Compute the empirical first moment \\bar\\xi_i=sum_j w_ij\\xi_ij and covariance tensor C_i=sum_j w_ij(\\xi_ij-\\bar\\xi_i)(\\xi_ij-\\bar\\xi_i)^T+\\epsilon I. Define centered offsets \\tilde\\xi_ij=\\xi_ij-\\bar\\xi_i so the first-order drift term is removed. For node features H, compute d_ij=H_j-H_i and directional derivatives delta_a H_i=sum_j w_ij\\tilde\\xi_ij,a d_ij. Use a second message-passing pass to approximate delta_a(delta_b H_i), then compute D_i H_i=0.5 sum_{a,b}(C_i)_{ab} delta_a(delta_b H_i). Add alpha D_i H_i to the original residual block, initializing alpha at zero and constraining it nonnegative with softplus. The mathematical quantities supplied by the paper are the first-moment drift decomposition and the second-moment principal symbol; moments, local frames, and derivatives are estimated empirically from neighborhoods. First test on an anisotropic synthetic-manifold classification task and ModelNet point-cloud classification, comparing ordinary mean aggregation, isotropic graph diffusion, and this layer at matched parameter count and FLOPs. Evaluate accuracy, sample efficiency, gradient-norm variance, sensitivity to neighborhood radius, and robustness to nonuniform point density. Success means improved accuracy or faster loss descent, especially when neighborhoods are anisotropic or sampling density varies.",
 "math_summary": "The paper studies the mean-value operator A_h f(x)=h^{-2}\\fint_{B(x,h)}(f(q)-f(x))\\,d\\mu(q), where B(x,h) is a metric ball of radius h, \\mu is a smooth positive measure, and f is a smooth test function. In local privileged coordinates \\xi, Taylor expansion gives A_h f(x) approximately equal to h^{-1}\\nabla f(x)^T m_h(x)+(1/2)\\,\\nabla^2 f(x):C_h(x), where m_h(x)=\\fint_{B(x,h)}\\xi(q)\\,d\\mu(q)/h is the rescaled first moment and C_h(x)=\\fint_{B(x,h)}\\xi(q)\\xi(q)^T\\,d\\mu(q)/h^2 is the normalized second-moment tensor. The paper states that convergence for every smooth test function is equivalent to convergence of the rescaled horizontal first moments; when this holds, the principal symbol is determined by the limiting second-moment tensor, while the drift changes explicitly with the choice of measure. The adaptation uses empirical neighborhood moments m_i and C_i, centers the neighborhood to eliminate the O(h^{-1}) drift, and applies the positive-semidefinite part of C_i as a local diffusion metric.",
 "math_tags": [
  "geometry",
  "differential-geometry",
  "linear-algebra",
  "numerical-analysis"
 ],
 "ml_areas": [
  "graph-nn",
  "embedding",
  "regularization"
 ],
 "paper": {
  "arxiv_id": "2609.02710",
  "arxiv_url": "https://arxiv.org/abs/2609.02710",
  "summary_what_math_gives_to_ml": "The paper provides a principled small-scale expansion for averaging over metric balls in equiregular sub-Riemannian geometry. Its transferable asset is the separation between a first-moment term, which creates drift and can destroy a clean Laplacian limit, and a normalized second-moment tensor, which determines anisotropic diffusion. This suggests a geometry-aware graph or point-cloud layer that estimates local first and second moments, removes spurious drift, and applies the resulting positive-semidefinite diffusion tensor instead of using isotropic neighborhoods. The most direct test is whether this moment-corrected layer improves stability and sample efficiency on data lying near anisotropic or nonholonomic manifolds.",
  "title": "Asymptotic mean value Laplacian on equiregular sub-Riemannian manifolds",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 5,
  "novelty": 6,
  "usefulness": 6
 },
 "solves": [
  "accuracy",
  "stability",
  "sample-efficiency"
 ],
 "title": "Moment-Corrected Sub-Riemannian Diffusion Layer",
 "url": "https://synthcore.org/idea/3076/moment-corrected-sub-riemannian-diffusion-layer",
 "verification": {
  "peer_reviewed": false,
  "status": "unverified",
  "status_label": "Unverified",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)",
  "verification_axes": {
   "benchmark_mechanism": {
    "confirmed": null,
    "tested": false
   },
   "practical_benchmark": {
    "beats_baseline": null,
    "tested": false
   },
   "toy_mechanism_gate": {
    "confirmed": null,
    "tested": false
   }
  }
 }
}