activity
20162026
most citedSampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo

19 citations · 89 across the 40 of their papers we have counts for

collaborators
Showing 2020Show all

5 papers · 1 filter

stat.CO2020★ 3 cited

Nonreversible MCMC from conditional invertible transforms: a complete recipe with convergence guarantees

Achille Thin, Nikita Kotelevskii, Christophe Andrieu +3

Markov Chain Monte Carlo (MCMC) is a class of algorithms to sample complex and high-dimensional probability distributions. The Metropolis-Hastings (MH) algorithm, the workhorse of…

math.ST2020★ 4 cited

Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical Bayesian approach. Part II: Theoretical Analysis

Valentin De Bortoli, Alain Durmus, Ana F. Vidal +1

This paper presents a detailed theoretical analysis of the three stochastic approximation proximal gradient algorithms proposed in our companion paper [49] to set regularization pa…

stat.ML2020★ 13 cited

Quantitative Propagation of Chaos for SGD in Wide Neural Networks

Valentin De Bortoli, Alain Durmus, Xavier Fontaine +1

In this paper, we investigate the limiting behavior of a continuous-time counterpart of the Stochastic Gradient Descent (SGD) algorithm applied to two-layer overparameterized neura…

math.OC2020

Convergence rates and approximation results for SGD and its continuous-time counterpart

Xavier Fontaine, Valentin De Bortoli, Alain Durmus

This paper proposes a thorough theoretical analysis of Stochastic Gradient Descent (SGD) with non-increasing step sizes. First, we show that the recursion defining SGD can be prova…

stat.ML2020★ 5 cited

MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference

Achille Thin, Nikita Kotelevskii, Jean-Stanislas Denain +4

In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC). This approach can be used with g…