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