Publications

Machine Learning

Statistical and Topological Properties of Sliced Probability Divergences

The idea of slicing divergences has been proven to be successful when comparing two probability measures in various machine learning applications including generative modeling, and consists in computing the expected value of a `base divergence'…

Kimia Nadjahi, Alain Durmus, Lénaïc Chizat, Soheil Kolouri, Shahin Shahrampour, Umut Şimşekli

Advances in Neural Processing Systems - 2020

Analysis of PDEs

GEOMETRIC ERGODICITY OF THE BOUNCY PARTICLE SAMPLER

The Bouncy Particle Sampler (BPS) is a Monte Carlo Markov Chain algorithm to sample from a target density known up to a multiplicative constant. This method is based on a kinetic piecewise deterministic Markov process for which the target measure is…

Alain Durmus, Arnaud Guillin, Pierre Monmarché

The Annals of Applied Probability - 2020

Artificial Intelligence

A FUNCTIONAL EQUATION WITH POLYNOMIAL SOLUTIONS AND APPLICATION TO NEURAL NETWORKS

We construct and discuss a functional equation with contraction property. The solutions are real univariate polynomials. The series solving the natural fixed point iterations have immediate interpretation in terms of Neural Networks with recursive…

Bruno Després, Matthieu Ancellin

Comptes Rendus. Mathématique - 2020

Distributed, Parallel, and Cluster Computing

SPAWN: An Iterative, Potentials-Based, Dynamic Scheduling and Partitioning Tool

Many applications of physics modeling use regular meshes on whichcomputations of highly variable cost over time can occur. Distributing the un-derlying cells over manycore architectures is a critical load balancing step thatshould be performed the…

Jean-Charles Papin, Christophe Denoual, Laurent Colombet, Raymond Namyst

International Journal of Parallel Programming - 2020

Chemical and Process Engineering

Modeling and Study of Hydrodynamic flow within the Preneutralizer Reactor using CFD Approach

S. Elmisaoui, L. Khamar, S. Benjelloun, M. Khamar, J.M. Ghidaglia

Computer Aided Chemical Engineering - 2020

Human health and pathology

Biopsychosocial determinants of visuospatial memory performance according to different spaces

Visuospatial memory (VSM) performance depends on intrinsic (biopsychosocial parameters) and extrinsic (space) factors. We aimed at characterizing the determinants of VSM performance according to space. Young healthy adults, 20 males and 41 females …

L. Bherer, M. Gallou-Guyot, S. Mandigout, J. Lacroix, D. Ricard, S. Buffat, D. Archambeau, G. Guéguin, A. Perrochon

Neuroscience Research - 2020

Life Sciences

Extraocular muscle positions in anterior plagiocephaly: V-pattern strabismus explained using geometric mophometrics

Romain Touzé, Yann Heuzé, Matthieu Robert, Dominique Brémond-Gignac, Charles-Joris Roux, Syril James, Giovanna Paternoster, Eric Arnaud, Roman Hossein Khonsari

British Journal of Ophthalmology - 2020

Functional Analysis

A characterization of proximity operators

We characterize proximity operators, that is to say functions that map a vector to a solution of a penalized least squares optimization problem. Proximity operators of convex penalties have been widely studied and fully characterized by Moreau. They…

Rémi Gribonval, Mila Nikolova

Journal of Mathematical Imaging and Vision - 2020

Mathematics

Microtubules (MT) a key target in oncology: mathematical modeling of anti-MT agents on cell migration

Microtubules (MTs) are protein filaments found in all eukaryotic cells which are crucial for many cellular processes including cell movement, cell differentiation, and cell division, making them a key target for anti-cancer treatment. In particular,…

Emilie Denicolai, Stéphane Honoré, Florence Hubert, Rémi Tesson

Mathematical Modelling of Natural Phenomena - 2020

Statistics Theory

Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation

Stochastic approximation methods play a central role in maximum likelihood estimation problems involving intractable likelihood functions, such as marginal likelihoods arising in problems with missing or incomplete data, and in parametric empirical…

Valentin de Bortoli, Alain Durmus, Marcelo Pereyra, Ana Fernandez Vidal

Statistics and Computing - 2020