{
 "artifacts": null,
 "category": "architecture",
 "description": "Replace dense aggregation over patches, points, or graph neighbors with a state-dependent positive quadrature rule. A latent encoder produces the current manifold coordinate z, a small controller chooses a subset of entities, and a convex redistribution step assigns nonnegative weights so that the subset preserves the full aggregation on a learned feature basis. The method is especially suitable for neural operators and vision attention where many spatial entities are redundant along the data manifold.",
 "formulas_latex": [
  "$$\\bm{d}^{\\mathrm{FE}}=\\bm{T}\\bm{d}+\\bm{\\hat{d}}$$",
  "$$\\mathbf{R}^{\\mathrm{FE}}(\\bm{d};\\bm{\\mu})=\\mathbf{F}^{\\mathrm{int}}(\\bm{d};\\bm{\\mu})-\\mathbf{F}^{\\mathrm{ext}}(\\bm{\\mu})$$",
  "$$b(z)=\\sum_{i=1}^{M}a_i\\phi_i(z),\\qquad A_S(z)=[\\phi_i(z)]_{i\\in S}$$",
  "$$w_S(z)=\\arg\\min_{w\\ge 0}\\left\\|A_S(z)w-b(z)\\right\\|_2^2+\\lambda\\left\\|w-a_S\\right\\|_2^2,\\qquad y_S(z)=\\sum_{i\\in S}w_i(z)v_i$$"
 ],
 "id": 3121,
 "implementation": "(1) Integration point: apply this to one expensive aggregation in a neural operator, point-cloud network, graph message-passing layer, or vision transformer. Let the input contain M entities with values v_i and positional or graph descriptors e_i. Compute a global latent z from a cheap pooled encoder or the previous layer. Do not use it initially for standard query-key attention; use it to select and quadrature-weight entities before the expensive value projection or message computation. (2) Pseudocode: initialize S with all entities or a fixed-weight coreset; compute phi_i=MLP_phi([e_i,z]) and b=sum_i a_i phi_i; while |S|\u003eK, tentatively remove each candidate i, solve w=argmin_{w\u003e=0} ||A_{S\\{i}}w-b||^2+lambda||w-a_{S\\{i}}||^2, and permanently remove the candidate with the smallest residual increase; at inference solve the final nonnegative quadratic program and return y=sum_{i in S} w_i v_i. For differentiable training, use a straight-through top-K mask and backpropagate through the unconstrained quadratic-program solution, or use a differentiable nonnegative solver. (3) Compute b and phi from the current latent z; estimate the subset offline on calibration batches, then train the controller and basis by minimizing task loss plus gamma||A_Sw-b||^2. The paper's mathematical contribution is the positive convex redistribution and greedy pruning; the basis, latent encoder, and K are engineering choices. (4) First experiment: use a 2D advection or Darcy neural operator and a small ViT on CIFAR-10. Compare dense aggregation, fixed top-K attention, and this method at K/M in {1/4,1/16,1/64}. Measure validation error, aggregation FLOPs, wall-clock latency, and moment residual. Success is at least 4x lower aggregation cost with less than 1 percentage point accuracy loss, plus stable nonnegative weights and lower error than random or fixed-weight selection at the same K.",
 "math_summary": "The paper represents the full state through an affine reduced coordinate map, $\\bm{d}^{\\mathrm{FE}}=\\bm{T}\\bm{d}+\\bm{\\hat d}$, where $\\bm{d}^{\\mathrm{FE}}\\in\\mathbb{R}^{N_{dof}}$ is the full state, $\\bm{d}\\in\\mathbb{R}^{N}$ is the reduced coordinate, $\\bm{T}$ is a lifting matrix, and $\\bm{\\hat d}$ contains prescribed data. Its full residual is $\\mathbf{R}^{\\mathrm{FE}}(\\bm d;\\bm\\mu)=\\mathbf F^{\\mathrm{int}}(\\bm d;\\bm\\mu)-\\mathbf F^{\\mathrm{ext}}(\\bm\\mu)$. MAW–ECM starts from a feasible fixed-weight empirical cubature rule and greedily removes entities; after each proposed removal it solves a convex quadratic weight-redistribution problem subject to local matching conditions and positivity. The neural adaptation treats each entity $i$ as carrying a feature vector $v_i\\in\\mathbb{R}^{p}$, uses a latent state $z\\in\\mathbb{R}^{r}$, and defines a state-conditioned basis $\\phi_i(z)\\in\\mathbb{R}^{q}$, for example $\\phi_i(z)=\\mathrm{MLP}_{\\phi}([e_i,z])$. The full target moments are $b(z)=\\sum_{i=1}^{M}a_i\\phi_i(z)$, where $a_i\u003e0$ are baseline area, patch, or degree weights. For a selected subset $S$, adaptive positive quadrature weights solve $\\min_{w\\ge 0}\\|A_S(z)w-b(z)\\|_2^2+\\lambda\\|w-a_S\\|_2^2$, where $A_S(z)=[\\phi_i(z)]_{i\\in S}$ and $a_S$ is the vector of baseline weights. The sparse aggregation is $y_S(z)=\\sum_{i\\in S}w_i(z)v_i$, while the dense reference is $y(z)=\\sum_{i=1}^{M}a_iv_i$. Positivity prevents cancellation and the moment constraint controls approximation error on the learned nonlinear manifold.",
 "math_tags": [
  "optimization",
  "convex-analysis",
  "approximation-theory",
  "geometry"
 ],
 "ml_areas": [
  "attention",
  "graph-nn",
  "inference-speedup",
  "world-model"
 ],
 "paper": {
  "arxiv_id": "2609.03068",
  "arxiv_url": "https://arxiv.org/abs/2609.03068",
  "summary_what_math_gives_to_ml": "The paper's transferable asset is a constructive way to compress a large collection of spatial entities while preserving quantities that vary over a nonlinear response manifold. Instead of assigning one globally fixed quadrature rule, it uses state-dependent positive weights and greedy removal, with each removal repaired by a convex quadratic redistribution problem. This suggests a sparse neural aggregation layer for point clouds, patches, graph neighborhoods, or neural operators that selects a small state-dependent subset while preserving learned feature moments, potentially reducing inference cost without relying on unconstrained negative attention weights.",
  "title": "Dimensional hyperreduction of nonlinear finite element models via empirical cubature with manifold-adaptive weights",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 6,
  "novelty": 6,
  "usefulness": 6
 },
 "solves": [
  "speedup",
  "memory",
  "accuracy"
 ],
 "title": "Manifold-Adaptive Positive Quadrature Attention",
 "url": "https://synthcore.org/idea/3121/manifold-adaptive-positive-quadrature-attention",
 "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
   }
  }
 }
}