Alain Durmus

发表

Bridging the gap between constant step size stochastic gradient descent and Markov chains

F. Bach, Aymeric Dieuleveut, Alain Durmus, 2017, The Annals of Statistics.

Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm

É. Moulines, Alain Durmus, 2015, 1507.05021.

High-dimensional Bayesian inference via the unadjusted Langevin algorithm

Alain Durmus, Eric Moulines, É. Moulines, 2016, Bernoulli.

Sampling from a strongly log-concave distribution with the Unadjusted Langevin Algorithm

É. Moulines, Alain Durmus, 2016 .

The tamed unadjusted Langevin algorithm

É. Moulines, Alain Durmus, N. Brosse, 2017, Stochastic Processes and their Applications.

Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize pdf

Eric Moulines, Alain Durmus, Hoi-To Wai, 2021, NeurIPS.

Statistical and Topological Properties of Sliced Probability Divergences pdf

Shahin Shahrampour, Alain Durmus, Umut Simsekli, 2020, NeurIPS.

Fast Langevin based algorithm for MCMC in high dimensions

G. Roberts, K. Zygalakis, Alain Durmus, 2015, 1507.02166.

Normalizing constants of log-concave densities

Alain Durmus, '. Moulines, N. Brosse, 2017, 1707.00460.

Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo

Eric Moulines, Roland Badeau, Alain Durmus, 2016, NIPS.

On the convergence of Hamiltonian Monte Carlo

É. Moulines, E. Saksman, Alain Durmus, 2017, 1705.00166.

Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions

Antoine Liutkus, Alain Durmus, Umut Şimşekli, 2018, ICML.

Invertible Flow Non Equilibrium sampling

Sylvain Le Corff, A. Doucet, É. Moulines, 2021, 2103.10943.

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

Eric Moulines, Christophe Andrieu, Alain Durmus, 2020, 2012.15550.

Diffusion Approximations and Control Variates for MCMC

Eric Moulines, Sean P. Meyn, Alain Durmus, 2018, Computational Mathematics and Mathematical Physics.

Statistical and Topological Properties of Sliced Probability Divergences pdf

Shahin Shahrampour, Alain Durmus, Soheil Kolouri, 2020, NeurIPS.

PR ] 1 5 Fe b 20 19 GEOMETRIC ERGODICITY OF THE BOUNCY PARTICLE SAMPLER

Alain Durmus, A. Guillin, Pierre Monmarché, 2022 .

Hypocoercivity of piecewise deterministic Markov process-Monte Carlo

Christophe Andrieu, Alain Durmus, Nikolas Nusken, 2018, The Annals of Applied Probability.

QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning

É. Moulines, Aymeric Dieuleveut, Alain Durmus, 2021, AISTATS.

Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation

É. Moulines, Alain Durmus, A. Naumov, 2022, 2207.04475.

FedPop: A Bayesian Approach for Personalised Federated Learning

É. Moulines, Alain Durmus, Maxime Vono, 2022, ArXiv.

Variational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical study

É. Moulines, Alain Durmus, Szymon Majewski, 2022, ArXiv.

Local-Global MCMC kernels: the best of both worlds

É. Moulines, Alain Durmus, A. Naumov, 2021, NeurIPS.

Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms

É. Moulines, Alain Durmus, Vincent Plassier, 2022, ArXiv.

Sticky nonlinear SDEs and convergence of McKean–Vlasov equations without confinement

Alain Durmus, A. Eberle, A. Guillin, 2022, Stochastics and Partial Differential Equations: Analysis and Computations.

Barrier Hamiltonian Monte Carlo

Valentin De Bortoli, Alain Durmus, Maxence Noble, 2022, ArXiv.

Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis Adjusted Langevin Algorithm

É. Moulines, Alain Durmus, 2014, Statistics and computing.

Quantitative Propagation of Chaos for SGD in Wide Neural Networks pdf

Alain Durmus, Valentin De Bortoli, Umut Simsekli, 2020, NeurIPS.

Maximum entropy methods for texture synthesis: theory and practice pdf

Bruno Galerne, Alain Durmus, Valentin De Bortoli, 2019, SIAM J. Math. Data Sci..

Continuous and Discrete-Time Analysis of Stochastic Gradient Descent for Convex and Non-Convex Functions.

Valentin De Bortoli, Alain Durmus, Xavier Fontaine, 2020, 2004.04193.

Hypocoercivity of piecewise deterministic Markov process-Monte Carlo

Christophe Andrieu, Alain Durmus, Nikolas Nusken, 2018, The Annals of Applied Probability.

Lattice Signatures and Bimodal Gaussians

Léo Ducas, Tancrède Lepoint, Alain Durmus, 2013, IACR Cryptol. ePrint Arch..

Convergence Analysis of Riemannian Stochastic Approximation Schemes

É. Moulines, Alain Durmus, Hoi-To Wai, 2020, arXiv.org.

Convergence Analysis of Riemannian Stochastic Approximation Schemes pdf

Alain Durmus, Salem Said, Hoi-To Wai, 2020, ArXiv.

Analysis of Langevin Monte Carlo via Convex Optimization

Alain Durmus, Blazej Miasojedow, Szymon Majewski, 2018, J. Mach. Learn. Res..

Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau

Eric Moulines, Alain Durmus, Marcelo Pereyra, 2016, SIAM J. Imaging Sci..

DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm pdf

Eric Moulines, Alain Durmus, Maxime Vono, 2021, ICML.

On Maximum a Posteriori Estimation with Plug & Play Priors and Stochastic Gradient Descent pdf

Julie Delon, Alain Durmus, Marcelo Pereyra, 2022, Journal of Mathematical Imaging and Vision.

Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie

Valentin De Bortoli, Alain Durmus, J. Delon, 2021, SIAM J. Imaging Sci..

Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach Part I: Methodology and Experiments

Valentin De Bortoli, Alain Durmus, M. Pereyra, 2019, SIAM J. Imaging Sci..

Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach. Part II: Theoretical Analysis

Alain Durmus, Valentin De Bortoli, Marcelo Pereyra, 2020, SIAM J. Imaging Sci..

Efficient stochastic optimisation by unadjusted Langevin Monte Carlo

Valentin De Bortoli, Alain Durmus, M. Pereyra, 2019, Statistics and Computing.

Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical Bayesian approach

Alain Durmus, Valentin De Bortoli, Marcelo Pereyra, 2019, 1911.11709.

NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform

Sylvain Le Corff, A. Doucet, É. Moulines, 2021, 2103.10943.

Forward Event-Chain Monte Carlo: Fast Sampling by Randomness Control in Irreversible Markov Chains

Alain Durmus, S. Sénécal, M. Michel, 2017, Journal of Computational and Graphical Statistics.

Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach

Alain Durmus, Giovanni Conforti, Giacomo Greco, 2023, 2304.06549.

FedPop: A Bayesian Approach for Personalised Federated Learning

É. Moulines, Alain Durmus, Maxime Vono, 2022, NeurIPS.

Convergence of diffusions and their discretizations: from continuous to discrete processes and back

Alain Durmus, Valentin De Bortoli, Alain Durmus, 2019, 1904.09808.

Markov Decision Process for MOOC Users Behavioral Inference

Vianney Perchet, Alain Durmus, Firas Jarboui, 2019, EMOOCs.

Monte Carlo Variational Auto-Encoders

Eric Moulines, Arnaud Doucet, Alain Durmus, 2021, ICML.

The promises and pitfalls of Stochastic Gradient Langevin Dynamics

Eric Moulines, Alain Durmus, Nicolas Brosse, 2018, NeurIPS.

High dimensional Markov chain Monte Carlo methods : theory, methods and applications

Alain Durmus, 2016 .

An elementary approach to uniform in time propagation of chaos

Alain Durmus, Arnaud Guillin, Andreas Eberle, 2018, Proceedings of the American Mathematical Society.

Piecewise deterministic Markov processes and their invariant measures

Alain Durmus, Arnaud Guillin, Pierre Monmarch'e, 2018, Annales de l'Institut Henri Poincaré, Probabilités et Statistiques.

Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo

Eric Moulines, Alain Durmus, Marcelo Pereyra, 2017, COLT.

Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections pdf

Roland Badeau, Alain Durmus, Pierre E. Jacob, 2021, NeurIPS.

Second order quantitative bounds for unadjusted generalized Hamiltonian Monte Carlo

Alain Durmus, G. Stoltz, Pierre Monmarch'e, 2023, ArXiv.

Asymptotic bias of inexact Markov Chain Monte Carlo methods in high dimension

Alain Durmus, A. Eberle, 2021, The Annals of Applied Probability.

Uniform minorization condition and convergence bounds for discretizations of kinetic Langevin dynamics

É. Moulines, Alain Durmus, G. Stoltz, 2021, ArXiv.

Optimal Scaling Results for a Wide Class of Proximal MALA Algorithms

G. Roberts, Alain Durmus, F. R. Crucinio, 2023, 2301.02446.

A Proximal Markov Chain Monte Carlo Method for Bayesian Inference in Imaging Inverse Problems: When Langevin Meets Moreau

É. Moulines, Alain Durmus, M. Pereyra, 2022, SIAM Rev..

On the geometric convergence for MALA under verifiable conditions pdf

Alain Durmus, Éric Moulines, É. Moulines, 2022, ArXiv.

Quantitative contraction rates for Sinkhorn algorithm: beyond bounded costs and compact marginals

Alain Durmus, Giovanni Conforti, Giacomo Greco, 2023, 2304.04451.

Subgeometric rates of convergence in Wasserstein distance for Markov chains

É. Moulines, Alain Durmus, G. Fort, 2014, 1402.4577.

On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning

Eric Moulines, Alain Durmus, Hoi-To Wai, 2021, COLT.

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

Alain Durmus, Valentin De Bortoli, Xavier Fontaine, 2021, COLT.

Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters

Valentin De Bortoli, A. Doucet, Alain Durmus, 2023, ArXiv.

Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach

Alain Durmus, Giovanni Conforti, Giacomo Greco, 2023, COLT.

Probability and moment inequalities for additive functionals of geometrically ergodic Markov chains

É. Moulines, Alain Durmus, A. Naumov, 2021, 2109.00331.

Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance

Roland Badeau, Alain Durmus, Umut Simsekli, 2019, NeurIPS.

Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo

Valentin De Bortoli, Alain Durmus, Maxence Noble, 2022, 2210.11925.

Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo

É. Moulines, E. Saksman, Alain Durmus, 2020 .

Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation

É. Moulines, Alain Durmus, A. Naumov, 2022, Mathematics of Operations Research.

Fast Bayesian Model Selection in Imaging Inverse Problems Using Residuals

Jean-François Giovannelli, Alain Durmus, Marcelo Pereyra, 2021, 2021 IEEE Statistical Signal Processing Workshop (SSP).

Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo

É. Moulines, Alain Durmus, M. Pereyra, 2018 .

On Riemannian Stochastic Approximation Schemes with Fixed Step-Size pdf

Alain Durmus, Salem Said, Éric Moulines, 2021, AISTATS.

Geometric ergodicity of the Bouncy Particle Sampler

Alain Durmus, A. Guillin, Pierre Monmarch'e, 2018, The Annals of Applied Probability.

On Sampling with Approximate Transport Maps

É. Moulines, Alain Durmus, Marylou Gabri'e, 2023, ICML.

Score diffusion models without early stopping: finite Fisher information is all you need

Alain Durmus, Giovanni Conforti, Marta Gentiloni Silveri, 2023, 2308.12240.

Parallelized Stochastic Gradient Markov Chain Monte Carlo algorithms for non-negative matrix factorization

Eric Moulines, Roland Badeau, Ali Taylan Cemgil, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

New conditions for subgeometric rates of convergence in the Wasserstein distance for Markov chains

É. Moulines, Alain Durmus, G. Fort, 2014 .

Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis Adjusted Langevin Algorithm

Eric Moulines, Alain Durmus, É. Moulines, 2014, Statistics and Computing.

Discrete sticky couplings of functional autoregressive processes

Alain Durmus, A. Eberle, A. Guillin, 2021, 2104.06771.

Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm

É. Moulines, Alain Durmus, 2015, 1507.05021.

Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections

Alain Durmus, P. Jacob, R. Badeau, 2021, NeurIPS.

Approximate Bayesian Computation with the Sliced-Wasserstein Distance

Valentin De Bortoli, Alain Durmus, R. Badeau, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

High-dimensional Bayesian inference via the unadjusted Langevin algorithm

É. Moulines, Alain Durmus, 2016, Bernoulli.

Rosenthal-type inequalities for linear statistics of Markov chains

É. Moulines, Alain Durmus, A. Naumov, 2023, 2303.05838.

Ring-LWE in Polynomial Rings

Léo Ducas, Alain Durmus, Alain Durmus, 2012, IACR Cryptol. ePrint Arch..

Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo

Valentin De Bortoli, Alain Durmus, Maxence Noble, 2022, NeurIPS.

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

Alain Durmus, Eric Moulines, Maxim Panov, 2020, ArXiv.

Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters

Valentin De Bortoli, A. Doucet, Alain Durmus, 2023, NeurIPS.

Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson-Romberg Extrapolation

Alain Durmus, S. Samsonov, Marina Sheshukova, 2024, 2410.05106.