works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

math.ST2026

Estimating conditional expectation

Hông Vân Lê

In this paper, we consider the problem of estimating conditional expectations as an ill-posed inverse problem. We propose a solution based on a generalization of Vapnik's theorem \…

math.DG2026

Empirical Hodge Laplacians: Spectral Convergence and Harmonic Forms from Point Clouds

Hông Vân Lê

The paper builds empirical Hodge Laplacians from uniformly sampled point clouds on a smooth manifold and proves they converge to the true Hodge Laplacian, enabling consistent recov…

math.ST2026

Batch learning equals online learning in Bayesian supervised learning

Hông Vân Lê

In this paper we study Bayesian supervised learning models proposed by Lê in \cite{Le2025}. Using functoriality of probabilistic morphisms, we prove that sequential and batch Baye…

math.ST2025

Probabilistic morphisms and Bayesian supervised learning

Hông Vân Lê

In this paper, we develop category theory of Markov kernels to study categorical aspects of Bayesian inversions. As a result, we present a unified model for Bayesian supervised lea…

stat.ML2025

Categorical and geometric methods in statistical, manifold, and machine learning

Hông Vân Lê, Hà Quang Minh, Frederic Protin +1

We present and discuss applications of the category of probabilistic morphisms, initially developed in \cite{Le2023}, as well as some geometric methods to several classes of proble…

math.AT2025

Unital -algebras and the real homotopy type of -connected compact manifolds of dimension

Domenico Fiorenza, Hông Vân Lê

We encode the real homotopy type of an -dimensional -connected compact manifold , into a minimal unital -structure on , obtained…