b'Eric Moulines'

research

∙ 08/15/2023

Monte Carlo guided Diffusion for Bayesian linear inverse problems

Ill-posed linear inverse problems that combine knowledge of the forward ...

0 Gabriel Cardoso, et al. ∙

research

∙ 07/10/2023

Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference

We provide a rigorous analysis of training by variational inference (VI)...

0 Arnaud Descours, et al. ∙

research

∙ 06/08/2023

Conformal Prediction for Federated Uncertainty Quantification Under Label Shift

Federated Learning (FL) is a machine learning framework where many clien...

0 Vincent Plassier, et al. ∙

research

∙ 06/01/2023

Balanced Training of Energy-Based Models with Adaptive Flow Sampling

Energy-based models (EBMs) are versatile density estimation models that ...

0 Louis Grenioux, et al. ∙

research

∙ 04/27/2023

One-Step Distributional Reinforcement Learning

Reinforcement learning (RL) allows an agent interacting sequentially wit...

0 Mastane Achab, et al. ∙

research

∙ 04/01/2023

Restarted Bayesian Online Change-point Detection for Non-Stationary Markov Decision Processes

We consider the problem of learning in a non-stationary reinforcement le...

0 Réda Alami, et al. ∙

research

∙ 03/16/2023

Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold

We consider the problem of minimizing a non-convex function over a smoot...

0 Sholom Schechtman, et al. ∙

research

∙ 03/14/2023

Fast Rates for Maximum Entropy Exploration

We consider the reinforcement learning (RL) setting, in which the agent ...

0 Daniil Tiapkin, et al. ∙

research

∙ 03/10/2023

Rosenthal-type inequalities for linear statistics of Markov chains

In this paper, we establish novel deviation bounds for additive function...

0 Alain Durmus, et al. ∙

research

∙ 02/22/2023

Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning

Stochastic approximation (SA) is a classical algorithm that has had sinc...

0 Aymeric Dieuleveut, et al. ∙

research

∙ 02/09/2023

On Sampling with Approximate Transport Maps

Transport maps can ease the sampling of distributions with non-trivial g...

0 Louis Grenioux, et al. ∙

research

∙ 01/02/2023

State and parameter learning with PaRIS particle Gibbs

Non-linear state-space models, also known as general hidden Markov model...

0 Gabriel Cardoso, et al. ∙

research

∙ 01/02/2023

Stochastic Variable Metric Proximal Gradient with variance reduction for non-convex composite optimization

This paper introduces a novel algorithm, the Perturbed Proximal Precondi...

0 Gersende Fort, et al. ∙

research

∙ 11/07/2022

AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks

In this paper, we develop a new algorithm, Annealed Skewed SGD - AskewSG...

0 Louis Leconte, et al. ∙

research

∙ 10/31/2022

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

This paper focuses on Bayesian inference in a federated learning context...

0 Vincent Plassier, et al. ∙

research

∙ 09/28/2022

Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees

We consider reinforcement learning in an environment modeled by an episo...

0 Daniil Tiapkin, et al. ∙

research

∙ 09/21/2022

Particle-based, rapid incremental smoother meets particle Gibbs

The particle-based, rapid incremental smoother (PARIS) is a sequential M...

0 Gabriel Cardoso, et al. ∙

research

∙ 07/13/2022

BR-SNIS: Bias Reduced Self-Normalized Importance Sampling

Importance Sampling (IS) is a method for approximating expectations unde...

0 Gabriel Cardoso, et al. ∙

research

∙ 07/10/2022

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

This paper provides a finite-time analysis of linear stochastic approxim...

0 Alain Durmus, et al. ∙

research

∙ 07/08/2022

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

This paper studies the Variational Inference (VI) used for training Baye...

0 Tom Huix, et al. ∙

research

∙ 06/07/2022

FedPop: A Bayesian Approach for Personalised Federated Learning

Personalised federated learning (FL) aims at collaboratively learning a ...

0 Nikita Kotelevskii, et al. ∙

research

∙ 05/16/2022

From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses

We propose the Bayes-UCBVI algorithm for reinforcement learning in tabul...

0 Daniil Tiapkin, et al. ∙

research

∙ 01/06/2022

On the geometric convergence for MALA under verifiable conditions

While the Metropolis Adjusted Langevin Algorithm (MALA) is a popular and...

0 Alain Durmus, et al. ∙

research

∙ 11/04/2021

Ex^2MCMC: Sampling through Exploration Exploitation

We develop an Explore-Exploit Markov chain Monte Carlo algorithm (Ex^2MC...

0 Evgeny Lagutin, et al. ∙

research

∙ 11/03/2021

Federated Expectation Maximization with heterogeneity mitigation and variance reduction

The Expectation Maximization (EM) algorithm is the default algorithm for...

0 Aymeric Dieuleveut, et al. ∙

research

∙ 07/30/2021

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

We study the convergence in total variation and V-norm of discretization...

0 Alain Durmus, et al. ∙

research

∙ 06/30/2021

Monte Carlo Variational Auto-Encoders

Variational auto-encoders (VAE) are popular deep latent variable models ...

0 Achille Thin, et al. ∙

research

∙ 06/11/2021

DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs

Performing reliable Bayesian inference on a big data scale is becoming a...

0 Vincent Plassier, et al. ∙

research

∙ 06/02/2021

Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize

This paper provides a non-asymptotic analysis of linear stochastic appro...

0 Alain Durmus, et al. ∙

research

∙ 06/01/2021

QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning

Federated learning aims at conducting inference when data are decentrali...

0 Maxime Vono, et al. ∙

research

∙ 05/25/2021

The Perturbed Prox-Preconditioned SPIDER algorithm for EM-based large scale learning

Incremental Expectation Maximization (EM) algorithms were introduced to ...

0 Gersende Fort, et al. ∙

research

∙ 03/17/2021

Invertible Flow Non Equilibrium sampling

Simultaneously sampling from a complex distribution with intractable nor...

0 Achille Thin, et al. ∙

research

∙ 02/15/2021

On Riemannian Stochastic Approximation Schemes with Fixed Step-Size

This paper studies fixed step-size stochastic approximation (SA) schemes...

0 Alain Durmus, et al. ∙

research

∙ 01/30/2021

Rates of convergence for density estimation with GANs

We undertake a precise study of the non-asymptotic properties of vanilla...

0 Denis Belomestny, et al. ∙

research

∙ 01/30/2021

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

This paper studies the exponential stability of random matrix products d...

0 Alain Durmus, et al. ∙

research

∙ 12/31/2020

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

Markov Chain Monte Carlo (MCMC) is a class of algorithms to sample compl...

0 Achille Thin, et al. ∙

research

∙ 11/30/2020

A Stochastic Path-Integrated Differential EstimatoR Expectation Maximization Algorithm

The Expectation Maximization (EM) algorithm is of key importance for inf...

0 Gersende Fort, et al. ∙

research

∙ 11/24/2020

Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization

The Expectation Maximization (EM) algorithm is a key reference for infer...

0 Gersende Fort, et al. ∙

research

∙ 05/27/2020

Convergence Analysis of Riemannian Stochastic Approximation Schemes

This paper analyzes the convergence for a large class of Riemannian stoc...

0 Alain Durmus, et al. ∙

research

∙ 02/27/2020

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

In this contribution, we propose a new computationally efficient method ...

76 Achille Thin, et al. ∙

research

∙ 02/04/2020

Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise

Linear two-timescale stochastic approximation (SA) scheme is an importan...

0 Maxim Kaledin, et al. ∙

research

∙ 01/22/2020

On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation

Uncertainty quantification for deep learning is a challenging open probl...

60 Nicolas Brosse, et al. ∙

research

∙ 10/30/2019

Unifying mirror descent and dual averaging

We introduce and analyse a new family of algorithms which generalizes an...

0 Anatoli Juditsky, et al. ∙

research

∙ 10/28/2019

On the Global Convergence of (Fast) Incremental Expectation Maximization Methods

The EM algorithm is one of the most popular algorithm for inference in l...

0 Belhal Karimi, et al. ∙

research

∙ 10/27/2019

f-SAEM: A fast Stochastic Approximation of the EM algorithm for nonlinear mixed effects models

The ability to generate samples of the random effects from their conditi...

0 Belhal Karimi, et al. ∙

research

∙ 07/05/2019

A quantitative Mc Diarmid's inequality for geometrically ergodic Markov chains

We state and prove a quantitative version of the bounded difference ineq...

0 Antoine Havet, et al. ∙

research

∙ 05/30/2019

On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case

We consider the problem of sampling from a target distribution which is ...

0 Ngoc Huy Chau, et al. ∙

research

∙ 02/02/2019

Non-asymptotic Analysis of Biased Stochastic Approximation Scheme

Stochastic approximation (SA) is a key method used in statistical learni...

0 Belhal Karimi, et al. ∙

research

∙ 12/20/2018

Low-rank Interaction with Sparse Additive Effects Model for Large Data Frames

Many applications of machine learning involve the analysis of large data...

0 Geneviève Robin, et al. ∙

research

∙ 11/25/2018

The promises and pitfalls of Stochastic Gradient Langevin Dynamics

Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC a...

0 Nicolas Brosse, et al. ∙

Eric Moulines

Featured Co-authors