T Wang - Information and Inference: A Journal of the IMA, 2023 - academic.oup.com
We study Hessian estimators for functions defined over an-dimensional complete analytic Riemannian manifold. We introduce new stochastic zeroth-order Hessian estimators using …
XL Li - arXiv preprint arXiv:2402.11858, 2024 - arxiv.org
This paper studies the fitting of Hessian or its inverse with stochastic Hessian-vector products. A Hessian fitting criterion, which can be used to derive most of the commonly used …
Y Feng, T Wang - Information and Inference: A Journal of the …, 2023 - academic.oup.com
We study stochastic zeroth-order gradient and Hessian estimators for real-valued functions in. We show that, via taking finite difference along random orthogonal directions, the …
IZ Pesenson - … on Sampling Theory and Applications (SampTA), 2017 - ieeexplore.ieee.org
The well known Weyl's asymptotic formula gives an approximation to the number N ω of eigenvalues (counted with multiplicities) on an interval [0, ω] of the Laplace-Beltrami …
C Genovese, M Perone-Pacifico, I Verdinelli… - arXiv preprint arXiv …, 2010 - arxiv.org
We find the minimax rate of convergence in Hausdorff distance for estimating a manifold M of dimension d embedded in R^ D given a noisy sample from the manifold. We assume that …
We propose nonparametric estimators for the second-order central moments of possibly anisotropic spherical random fields, within a functional data analysis context. We consider a …
IZ Pesenson - … and Partial Differential Equations: Perspectives from …, 2019 - Springer
The well known Weyl's asymptotic formula gives an approximation to the number N _ ω of eigenvalues (counted with multiplicities) on an interval 0,\, ω of an elliptic second-order …
By methods of stochastic analysis on Riemannian manifolds, we develop two approaches to determine an explicit constant $ c (D) $ for an $ n $-dimensional compact manifold $ D …
M Korte-Stapff, T Karvonen, E Moulines - arXiv preprint arXiv:2401.00510, 2023 - arxiv.org
The family of Mat\'ern kernels are often used in spatial statistics, function approximation and Gaussian process methods in machine learning. One reason for their popularity is the …