88 citations · 487 across the 78 of their papers we have counts for
8 papers · 1 filter
The promises and pitfalls of Stochastic Gradient Langevin Dynamics
Nicolas Brosse, Alain Durmus, Eric Moulines
Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC algorithm for Bayesian learning from large scale datasets. While SGLD with decreasing step sizes converges we…
Hypocoercivity of Piecewise Deterministic Markov Process-Monte Carlo
Christophe Andrieu, Alain Durmus, Nikolas Nüsken +1
In this work, we establish -exponential convergence for a broad class of Piecewise Deterministic Markov Processes recently proposed in the context of Markov Process M…
Diffusion approximations and control variates for MCMC
Nicolas Brosse, Alain Durmus, Sean Meyn +2
A new methodology is presented for the construction of control variates to reduce the variance of additive functionals of Markov Chain Monte Carlo (MCMC) samplers. Our control vari…
Piecewise Deterministic Markov Processes and their invariant measures
Alain Durmus, Arnaud Guillin, Pierre Monmarché
Piecewise Deterministic Markov Processes (PDMPs) are studied in a general framework. First, different constructions are proven to be equivalent. Second, we introduce a coupling bet…
Geometric ergodicity of the bouncy particle sampler
Alain Durmus, Arnaud Guillin, Pierre Monmarché
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 p…
Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions
Antoine Liutkus, Umut Şimşekli, Szymon Majewski +2
By building upon the recent theory that established the connection between implicit generative modeling (IGM) and optimal transport, in this study, we propose a novel parameter-fre…
An Elementary Approach To Uniform In Time Propagation Of Chaos
Alain Durmus, Andreas Eberle, Arnaud Guillin +1
Based on a coupling approach, we prove uniform in time propagation of chaos for weakly interacting mean-field particle systems with possibly non-convex confinement and interaction…
Analysis of Langevin Monte Carlo via convex optimization
Alain Durmus, Szymon Majewski, Błażej Miasojedow
In this paper, we provide new insights on the Unadjusted Langevin Algorithm. We show that this method can be formulated as a first order optimization algorithm of an objective func…