Paperlane

no. 17 · Wednesday 18 November 2026

Differentiable High-Order Mesh $r$-Adaptivity

Ketan Mittal, Julian Andrej, John Camier, Veselin Dobrev, Tzanio Kolev, Leonardo Molinari and Vladimir Tomov

math.NA · 14 pp

Abstract

High-order mesh r-adaptivity typically entails minimizing a nonlinear functional using its gradients and, for Newton-based methods, its Hessian. These derivatives can be expensive to derive, must be updated with any changes to the functional, and errors in the derivatives directly impact the convergence of r-adaptivity. Additionally, derivatives of the r-adaptivity operator are required for consistent sensitivity analysis for inverse problems. This work develops a framework for differentiable r-adaptivity based on the Target-Matrix Optimization Paradigm. Given a pointwise functional defining the local mesh-adaptation objective, the proposed framework uses $\partial$FEM to automatically generate pointwise first- and second-order derivatives. These local derivatives are then assembled into a global gradient vector and a Hessian operator through the finite element operator decomposition. The derivative kernels support portable CPU and GPU execution, with partial assembly and tensor sum factorization enabling matrix-free application of the Hessian operator. The framework also provides consistent sensitivities of the r-adaptivity operator through automatically generated mixed derivatives and implicit differentiation of the mesh stationarity equations. Numerical experiments show GPU solve times comparable to those of hand-derived TMOP implementations on a benchmark problem, improvement in r-adaptivity convergence due to accurate computation of the derivatives, and demonstrate the use of mesh sensitivities for material-interface identification in an inverse heat-conduction problem.

comments
14 pages, 10 figures, 2 tables
fields
Numerical Analysis
pdf ↗ page arXiv:2611.22099 ↗