CORTEXA
← Browse
arxivmath.NAcs.LGmath.AP2026-07-15Cited by 0

Approximation of solutions of parameter-dependent problems by residual neural networks

Ana Carpio

We develop a convergent scheme to train neural networks involving analytic activation functions based on gradient flows. Convergence properties are guaranteed by Lojasiewicz theory. The main advantage of this approach is its simplicity of implementation. The coefficients of the network are approximated by solving a system of ordinary differential equations. We test the method by constructing residual neural network approximations of solutions of parametric problems. The dependence of the solutions of simple ordinary differential equations on a few parameters is correctly reproduced. The solutions of inverse problems involving wave constraints which depend on a few parameters can be reasonably approximated, even in regions in which the problem is severely ill posed.

View free PDFSource page

Related papers

arxivcs.LGmath.NA2026-07-22

PG-KINN: A Physics-Informed Petrov-Galerkin Kolmogorov-Arnold Network for Solving Forward and Inverse PDEs

Amirhossein Sadr, Nima Soltani, Vahideh Moghtadaiee, Aida Pakniyat, Dara Rahmati, Saeid Gorgin

Physics-informed learning of partial differential equations (PDEs) has been dominated by multilayer perceptrons (MLPs), whose spectral bias and dense parameterization limit both accuracy and interpretability. Kolmogorov Arnold Networks (KANs) mitigate these limitations because th…

View free PDFSource page
arxivcs.LGeess.SPmath.NA2026-07-24

Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement

Guoming Li, Jian Yang, Xukun Wang, Zixiao Wang, Shangsong Liang, Yifan Chen

Coarsening-based training for graph neural networks (GNNs), i.e.\ training on coarsened graphs rather than the original large ones, has become a promising direction for scaling GNNs to massive graphs. However, prior work has been evaluated almost exclusively on \textit{homophilic…

View free PDFSource page
arxivcs.LGmath.NA2026-07-31

Freeze, Then Select: Structured Field Adapters and Stability-Validated Weak Selection for PDE Discovery from Sparse Observations

Juncheng Zhong, Chenghuang Shen, Jianfeng Liu, Zhengdong Xiao, Longjiu Luo, Qianrong Wang, et al.

PDE discovery from sparse observations requires reconstructing a continuous field and selecting the correct differential terms. Our analysis of optimization paths in coupled neural PDE discovery reveals three behaviors: the exact support can persist to the end of training, appear…

View free PDFSource page
arxivstat.MLcs.LGmath.NAstat.CO2026-07-24

Convergence analysis of a family of Zermelo-type iterations for the Bradley--Terry model

Ruijian Han, Ding Lu, Yiming Xu

Zermelo's algorithm is a classical method for computing the maximum likelihood estimator in the Bradley--Terry (BT) model, but its convergence can be slow in practice. To accelerate computation, Newman introduced a family of Zermelo-type fixed-point iterations parameterized by $α…

View free PDFSource page
arxivstat.MLcs.LGmath.NAmath.ST2026-07-31

Simple-regret rates and minimax optimality of fixed-prior expected improvement in Matérn and squared-exponential RKHSs

Emmanuel Vazquez, Sébastien Petit

We study the expected improvement (EI) policy for minimizing a deterministic objective function $f$ on a nonempty compact set $\mathcal X \subset\mathbb R^d$. We assume that $f$ belongs to the RKHS $\mathcal H_k$ of a continuous positive-semidefinite kernel $k$ on $\mathcal X$. F…

View free PDFSource page