activity
20242026
collaborators

5 papers

math.PR2026

On quantitative Laplace-type convergence results for some exponential probability measures, with two applications

Valentin De Bortoli, Agnès Desolneux

Laplace-type results characterize the limit of sequence of measures with density w.r.t the Lebesgue measure $(\mathrm{d} π_\varepsilon / \mathr…

stat.ML2026

Repulsive Monte Carlo on the sphere for the sliced Wasserstein distance

Vladimir Petrovic, Rémi Bardenet, Agnès Desolneux

In this paper, we consider the problem of computing the integral of a function on the unit sphere, in any dimension, using Monte Carlo methods. Although the methods we present are…

cs.LG2025

Differentiable Expectation-Maximisation and Applications to Gaussian Mixture Model Optimal Transport

Samuel Boïté, Eloi Tanguy, Julie Delon +2

The Expectation-Maximisation (EM) algorithm is a central tool in statistics and machine learning, widely used for latent-variable models such as Gaussian Mixture Models (GMMs). Des…

math.OC2025

Constrained Approximate Optimal Transport Maps

Eloi Tanguy, Agnès Desolneux, Julie Delon

We investigate finding a map within a function class that minimises an Optimal Transport (OT) cost between a target measure and the image by of a source measure $Î…

stat.ML2024

Gromov-Wasserstein-like Distances in the Gaussian Mixture Models Space

Antoine Salmona, Julie Delon, Agnès Desolneux

The Gromov-Wasserstein (GW) distance is frequently used in machine learning to compare distributions across distinct metric spaces. Despite its utility, it remains computationally…