Approximation of Hilbert-valued Gaussians on Dirichlet structures
S Bourguin, S Campese - 2020 - projecteuclid.org
We introduce a framework to derive quantitative central limit theorems in the context of non-
linear approximation of Gaussian random variables taking values in a separable Hilbert …
linear approximation of Gaussian random variables taking values in a separable Hilbert …
[HTML][HTML] Malliavin–Stein method: a survey of some recent developments
Initiated around the year 2007, the Malliavin–Stein approach to probabilistic approximations
combines Stein's method with infinite-dimensional integration by parts formulae based on …
combines Stein's method with infinite-dimensional integration by parts formulae based on …
Bound for an Approximation of Invariant Density of Diffusions via Density Formula in Malliavin Calculus
YT Kim, HS Park - Mathematics, 2023 - mdpi.com
The Kolmogorov and total variation distance between the laws of random variables have
upper bounds represented by the L 1-norm of densities when random variables have …
upper bounds represented by the L 1-norm of densities when random variables have …
[HTML][HTML] Normal approximation when a chaos grade is greater than two
YT Kim, HS Park - Statistics & Probability Letters, 2022 - Elsevier
We derive an upper bound on a probabilistic distance for a normal approximation when the
chaos grade of an eigenfunction of Markov diffusion generator L is greater than 2. When a …
chaos grade of an eigenfunction of Markov diffusion generator L is greater than 2. When a …
Improved Bound of Four Moment Theorem and Its Application to Orthogonal Polynomials Associated with Laws
YT Kim, HS Park - Axioms, 2023 - mdpi.com
In the case where the square of an eigenfunction F with respect to an eigenvalue of Markov
generator L can be expressed as a sum of eigenfunctions, we find the largest number …
generator L can be expressed as a sum of eigenfunctions, we find the largest number …
A quantitative functional central limit theorem for shallow neural networks
V Cammarota, D Marinucci, M Salvi… - … Stochastics: Theory and …, 2023 - vmsta.org
We prove a quantitative functional central limit theorem for one-hidden-layer neural
networks with generic activation function. Our rates of convergence depend heavily on the …
networks with generic activation function. Our rates of convergence depend heavily on the …
Non-central limit of densities of some functionals of Gaussian processes
S Bourguin, T Dang, Y Hu - arXiv preprint arXiv:2406.12722, 2024 - arxiv.org
We establish the convergence of the densities of a sequence of nonlinear functionals of an
underlying Gaussian process to the density of a Gamma distribution. We provide precise …
underlying Gaussian process to the density of a Gamma distribution. We provide precise …
Malliavin-Stein method: a survey of recent developments
Initiated around the year 2007, the Malliavin-Stein approach to probabilistic approximations
combines Stein's method with infinite-dimensional integration by parts formulae based on …
combines Stein's method with infinite-dimensional integration by parts formulae based on …
On non-stationary Wishart matrices and functional Gaussian approximations in Hilbert spaces
T Dang - 2022 - search.proquest.com
This thesis contains two main chapters. The first chapter focuses on the highdimensional
asymptotic regimes of correlated Wishart matrices d− 1 𝒴𝒴 T, where 𝒴 is an× d Gaussian …
asymptotic regimes of correlated Wishart matrices d− 1 𝒴𝒴 T, where 𝒴 is an× d Gaussian …
Quantitative Fourth Moment Theorem of Functions on the Markov Triple and Orthogonal Polynomials
YT Kim, HS Park - Journal of Function Spaces, 2021 - Wiley Online Library
In this paper, we consider a quantitative fourth moment theorem for functions (random
variables) defined on the Markov triple (E, μ, Γ), where μ is a probability measure and Γ is …
variables) defined on the Markov triple (E, μ, Γ), where μ is a probability measure and Γ is …