44 citations · 95 across the 8 of their papers we have counts for
10 papers
Universal Local Error and Realized Amplification for the First-Order EDM Predictor
Nicolas Brosse, Arnak S. Dalalyan
We analyze the first-order deterministic diffusion sampler of Karras et al. (2022), termed EDM, in 2-Wasserstein distance by separating two sources of error: local discretization e…
Boundary-layer asymptotics for Gaussian-smoothed singular measures
Nicolas Brosse, Arnak S. Dalalyan
We study the small-noise asymptotics of Euclidean heat regularizations of probability measures supported on manifolds with corners. Near a boundary or corner stratum, the relevant…
On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation
Nicolas Brosse, Carlos Riquelme, Alice Martin +2
Uncertainty quantification for deep learning is a challenging open problem. Bayesian statistics offer a mathematically grounded framework to reason about uncertainties; however, ap…
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…
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…
The Tamed Unadjusted Langevin Algorithm
Nicolas Brosse, Alain Durmus, Éric Moulines +1
In this article, we consider the problem of sampling from a probability measure having a density on known up to a normalizing constant, $x\mapsto \mathrm{e}^{-U(…
Normalizing constants of log-concave densities
Nicolas Brosse, Alain Durmus, Éric Moulines
We derive explicit bounds for the computation of normalizing constants for log-concave densities with respect to the Lebesgue measure on . Our app…
Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo
Nicolas Brosse, Alain Durmus, Éric Moulines +1
This paper presents a detailed theoretical analysis of the Langevin Monte Carlo sampling algorithm recently introduced in Durmus et al. (Efficient Bayesian computation by proximal…
Experimental study of a three dimensional cylinder-filament system
Nicolas Brosse, Carl Finmo, Fredrik Lundell +1
This experimental study reports on the behavior of a filament attached to the rear of a three- dimensional cylinder. The axis of the cylinder is placed normal to a uniform incoming…
Wake interaction of two disks falling in tandem
N. Brosse, S. Cazin, P. Ern
The fluid dynamics video illustrates the interaction of two disks falling in tandem at Reynolds number close to 100. Two fluorescent dyes were used to visualize the wake of each bo…