Add to ORKGInternational audienceIn this paper, we propose algorithms for sampling from the distributions whose density is non-smoothed nor log-concave. Our algorithms are based on the Langevin diffusion on the regularized counterpart of density by the Moreau-Yosida regularization. These results are then applied for computing the exponentially weighted aggregates for high dimensional regression
The first part of this thesis concerns the inference of un-normalized statistical models. We study t...
For many practical problems it is useful to be able to sample conditioned diffusions on a computer (...
Sampling from probability distributions is a problem of significant importance in Statistics and Mac...
National audienceIn this paper, we propose algorithms for sampling from the distributions whose dens...
International audienceIn this paper, we propose proximal splitting-type algorithms for sampling from...
For sampling from a log-concave density, we study implicit integrators resulting from θ- method disc...
This thesis focuses on the problem of sampling in high dimension and is based on the unadjusted Lang...
International audienceIn this paper, two new algorithms to sample from possibly non-smooth log-conca...
International audienceThis paper presents a detailed theoretical analysis of the Langevin Monte Carl...
International audienceWe extend the Langevin Monte Carlo (LMC) algorithm to compactly supported meas...
This paper presents two new Langevin Markov chain Monte Carlo methods that use con-vex analysis to s...
In this paper, we analyse a proximal method based on the idea of forward–backward splitting for samp...
A well-known first-order method for sampling from log-concave probability distributions is the Unadj...
For many practical problems it is useful to be able to sample conditioned diffusions on a computer (...
The first part of this thesis concerns the inference of un-normalized statistical models. We study t...
For many practical problems it is useful to be able to sample conditioned diffusions on a computer (...
Sampling from probability distributions is a problem of significant importance in Statistics and Mac...
National audienceIn this paper, we propose algorithms for sampling from the distributions whose dens...
International audienceIn this paper, we propose proximal splitting-type algorithms for sampling from...
For sampling from a log-concave density, we study implicit integrators resulting from θ- method disc...
This thesis focuses on the problem of sampling in high dimension and is based on the unadjusted Lang...
International audienceIn this paper, two new algorithms to sample from possibly non-smooth log-conca...
International audienceThis paper presents a detailed theoretical analysis of the Langevin Monte Carl...
International audienceWe extend the Langevin Monte Carlo (LMC) algorithm to compactly supported meas...
This paper presents two new Langevin Markov chain Monte Carlo methods that use con-vex analysis to s...
In this paper, we analyse a proximal method based on the idea of forward–backward splitting for samp...
A well-known first-order method for sampling from log-concave probability distributions is the Unadj...
For many practical problems it is useful to be able to sample conditioned diffusions on a computer (...
The first part of this thesis concerns the inference of un-normalized statistical models. We study t...
For many practical problems it is useful to be able to sample conditioned diffusions on a computer (...
Sampling from probability distributions is a problem of significant importance in Statistics and Mac...