488 citations · 3k across the 119 of their papers we have counts for
14 papers · 1 filter
Federated Expectation Maximization with heterogeneity mitigation and variance reduction
Aymeric Dieuleveut, Gersende Fort, Eric Moulines +1
The Expectation Maximization (EM) algorithm is the default algorithm for inference in latent variable models. As in any other field of machine learning, applications of latent vari…
Local-Global MCMC kernels: the best of both worlds
Sergey Samsonov, Evgeny Lagutin, Marylou Gabrié +3
Recent works leveraging learning to enhance sampling have shown promising results, in particular by designing effective non-local moves and global proposals. However, learning accu…
Probability and moment inequalities for additive functionals of geometrically ergodic Markov chains
Alain Durmus, Eric Moulines, Alexey Naumov +1
In this paper, we establish moment and Bernstein-type inequalities for additive functionals of geometrically ergodic Markov chains. These inequalities extend the corresponding ineq…
Uniform minorization condition and convergence bounds for discretizations of kinetic Langevin dynamics
Alain Durmus, Aurélien Enfroy, Éric Moulines +1
We study the convergence in total variation and -norm of discretization schemes of the underdamped Langevin dynamics. Such algorithms are very popular and commonly used in molec…
Monte Carlo Variational Auto-Encoders
Achille Thin, Nikita Kotelevskii, Arnaud Doucet +3
Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO). To obtain tighter ELBO and hence better vari…
DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs
Vincent Plassier, Maxime Vono, Alain Durmus +1
Performing reliable Bayesian inference on a big data scale is becoming a keystone in the modern era of machine learning. A workhorse class of methods to achieve this task are Marko…
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize
Alain Durmus, Eric Moulines, Alexey Naumov +3
This paper provides a non-asymptotic analysis of linear stochastic approximation (LSA) algorithms with fixed stepsize. This family of methods arises in many machine learning tasks…
QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning
Maxime Vono, Vincent Plassier, Alain Durmus +2
The objective of Federated Learning (FL) is to perform statistical inference for data which are decentralised and stored locally on networked clients. FL raises many constraints wh…
The perturbed prox-preconditioned spider algorithm: non-asymptotic convergence bounds
Gersende Fort, E Moulines
A novel algorithm named Perturbed Prox-Preconditioned SPIDER (3P-SPIDER) is introduced. It is a stochastic variancereduced proximal-gradient type algorithm built on Stochastic Path…
The Perturbed Prox-Preconditioned SPIDER algorithm for EM-based large scale learning
Gersende Fort, Eric Moulines
Incremental Expectation Maximization (EM) algorithms were introduced to design EM for the large scale learning framework by avoiding the full data set to be processed at each itera…
NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform
Achille Thin, Yazid Janati, Sylvain Le Corff +5
Sampling from a complex distribution and approximating its intractable normalizing constant Z are challenging problems. In this paper, a novel family of importance samplers (IS…
On Riemannian Stochastic Approximation Schemes with Fixed Step-Size
Alain Durmus, Pablo Jiménez, Éric Moulines +1
This paper studies fixed step-size stochastic approximation (SA) schemes, including stochastic gradient schemes, in a Riemannian framework. It is motivated by several applications,…
Rates of convergence for density estimation with generative adversarial networks
Nikita Puchkin, Sergey Samsonov, Denis Belomestny +2
In this work we undertake a thorough study of the non-asymptotic properties of the vanilla generative adversarial networks (GANs). We prove an oracle inequality for the Jensen-Shan…
On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning
Alain Durmus, Eric Moulines, Alexey Naumov +2
This paper studies the exponential stability of random matrix products driven by a general (possibly unbounded) state space Markov chain. It is a cornerstone in the analysis of sto…