A weighted FOSLS formulation for deep neural networks solves transmission problems robustly, with proofs that the loss aligns with the energy norm independently of material contrast and shows passive variance reduction.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
math.NA 2years
2026 2roles
background 1polarities
background 1representative citing papers
ℓFEM is a loop-free MATLAB package implementing isoparametric bulk and surface finite elements with high-order support, assembly details, and performance tests.
citing papers explorer
-
Robust Deep FOSLS for Transmission Problems
A weighted FOSLS formulation for deep neural networks solves transmission problems robustly, with proofs that the loss aligns with the energy norm independently of material contrast and shows passive variance reduction.
-
$\ell$FEM: An efficient loop-free Matlab implementation of isoparametric bulk and surface finite elements
ℓFEM is a loop-free MATLAB package implementing isoparametric bulk and surface finite elements with high-order support, assembly details, and performance tests.