Laboratoire de Mathématiques Raphaël Salem

UMR 6085 CNRS - Université de Rouen Normandie

Hamiltonian Monte Carlo (HMC) is a widely used sampler, known for its efficiency on high dimensional distributions. Yet HMC remains quite sensitive to the choice of integration time. Randomizing the length of Hamiltonian trajectories (RHMC) has been suggested to smooth the Auto-Correlation Functions (ACF), ensuring robustness of tuning. We present the Langevin diffusion as an alternative to control these ACFs by inducing randomness in Hamiltonian trajectories through a continuous refreshment of the velocities.

Cet exposé est basé sur un article de David Griffeath: A maximal coupling for Markov chains, dont le sujet est le couplage de chaînes de Markov, c'est-à-dire la loi jointe de copies de la chaîne de Markov qui partent respectivement de points $i$ et $j$. Un tel couplage est considéré comme gagnant si, pour tous points de départ $i$ et $j$, les deux copies de la chaîne de Markov finissent par se rencontrer presque sûrement.

Dans cet exposé, nous présenterons le théorème ergodique pour des U-statistiques d'ordre deux : des conditions suffisantes pour la
convergence presque sûre et dans $L^1$ ainsi que des exemples montrant que la convergence ne peut pas avoir lieu en général. Les résultats présentés
sont ceux de l'article https://arxiv.org/abs/2302.04539, réalisé en collaboration avec Herold Dehling et Dalibor Volny.

In this talk we analyze the homogenization process of a problem studied by Dominique Blanchard, Luciano Carbone and Antonio Gaudiello. A possible approach in the case of a less regular data will also be discussed

We consider truncated detection problems for statistical models with dependent observations given by Bayesian Markov chains for a uniform prior distribution when the number of observations is limited by some known value.

The space of measures with finite second moment, when endowed with the Wasserstein distance, is a geodesic space but not a vector space. Therefore, building an adequate differential calculus is not straightforward, and currently subject of debate in the literature. We review the main definitions in use in the Hamilton-Jacobi and Mean Fields communities, with examples illustrating the nature of the objects and comments on the range and limitations of each point of view. 

We introduce a new stochastic partial differential equation with second- order elliptic operator in divergence form, having a piecewise constant diffusion coefficient, and driven by different Gaussian noise. Such equation could be used in mathematical modeling of diffusion phenomena in medium consisting of two kinds of materials and undergoing stochastic perturbations. We prove the existence of the solution and we present explicit expressions of its covariance and variance functions.

We consider a non-local approximation of the time-dependent Eikonal equation defined on a Riemannian manifold. We show that the local and the non-local problems are well-posed in the sense of viscosity solutions and we prove regularity properties of these solutions in time and space. If the kernel is properly scaled, we then derive error bounds between the solution of the non-local problem and the one of the local problem, both in continuous-time and Forward Euler discretization. Finally, we apply these results to a sequence of random weighted graphs with $n$ vertices.