English

Simplex-FEM Networks (SiFEN): Learning A Triangulated Function Approximator

Machine Learning 2026-01-09 v2

Abstract

We introduce Simplex-FEM Networks (SiFEN), a learned piecewise-polynomial predictor that represents f: R^d -> R^k as a globally C^r finite-element field on a learned simplicial mesh in an optionally warped input space. Each query activates exactly one simplex and at most d+1 basis functions via barycentric coordinates, yielding explicit locality, controllable smoothness, and cache-friendly sparsity. SiFEN pairs degree-m Bernstein-Bezier polynomials with a light invertible warp and trains end-to-end with shape regularization, semi-discrete OT coverage, and differentiable edge flips. Under standard shape-regularity and bi-Lipschitz warp assumptions, SiFEN achieves the classic FEM approximation rate M^(-m/d) with M mesh vertices. Empirically, on synthetic approximation tasks, tabular regression/classification, and as a drop-in head on compact CNNs, SiFEN matches or surpasses MLPs and KANs at matched parameter budgets, improves calibration (lower ECE/Brier), and reduces inference latency due to geometric locality. These properties make SiFEN a compact, interpretable, and theoretically grounded alternative to dense MLPs and edge-spline networks.

Keywords

Cite

@article{arxiv.2511.04804,
  title  = {Simplex-FEM Networks (SiFEN): Learning A Triangulated Function Approximator},
  author = {Chaymae Yahyati and Ismail Lamaakal and Khalid El Makkaoui and Ibrahim Ouahbi and Yassine Maleh},
  journal= {arXiv preprint arXiv:2511.04804},
  year   = {2026}
}

Comments

We will improve our work soon

R2 v1 2026-07-01T07:25:21.211Z