88 citations · 487 across the 78 of their papers we have counts for
31 papers · 1 filter
Iterating Consistency Models: Stability, Error Bounds and Noise Schedules
Alessio Spagnoletti, Abdul-Lateef Haji-Ali, Andrés Almansa +3
Consistency models (CMs) have become a leading approach for generating high-quality samples in few steps. However, adding steps can improve or degrade sample quality in ways that a…
Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
Paul Mangold, Alain Durmus, Aymeric Dieuleveut +1
This paper proposes a novel analysis for the Scaffold algorithm, a popular method for dealing with data heterogeneity in federated learning. While its convergence in deterministic…
A Mixture-Based Framework for Guiding Diffusion Models
Yazid Janati, Badr Moufad, Mehdi Abou El Qassime +3
Denoising diffusion models have driven significant progress in the field of Bayesian inverse problems. Recent approaches use pre-trained diffusion models as priors to solve a wide…
Refined Analysis of Federated Averaging and Federated Richardson-Romberg
Paul Mangold, Alain Durmus, Aymeric Dieuleveut +2
In this paper, we present a novel analysis of \FedAvg with constant step size, relying on the Markov property of the underlying process. We demonstrate that the global iterates of…
Variational Diffusion Posterior Sampling with Midpoint Guidance
Badr Moufad, Yazid Janati, Lisa Bedin +4
Diffusion models have recently shown considerable potential in solving Bayesian inverse problems when used as priors. However, sampling from the resulting denoising posterior distr…
Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians
Tom Huix, Anna Korba, Alain Durmus +1
Variational inference (VI) is a popular approach in Bayesian inference, that looks for the best approximation of the posterior distribution within a parametric family, minimizing a…
Incentivized Learning in Principal-Agent Bandit Games
Antoine Scheid, Daniil Tiapkin, Etienne Boursier +5
This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent. The principal and the agent have misaligne…
Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors
Yazid Janati, Badr Moufad, Alain Durmus +2
Recent advancements in solving Bayesian inverse problems have spotlighted denoising diffusion models (DDMs) as effective priors. Although these have great potential, DDM priors yie…
VITS : Variational Inference Thompson Sampling for contextual bandits
Pierre Clavier, Tom Huix, Alain Durmus
In this paper, we introduce and analyze a variant of the Thompson sampling (TS) algorithm for contextual bandits. At each round, traditional TS requires samples from the current po…
Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters
Maxence Noble, Valentin De Bortoli, Arnaud Doucet +1
Multi-marginal Optimal Transport (mOT), a generalization of OT, aims at minimizing the integral of a cost function with respect to a distribution with some prescribed marginals. In…
On Sampling with Approximate Transport Maps
Louis Grenioux, Alain Durmus, Éric Moulines +1
Transport maps can ease the sampling of distributions with non-trivial geometries by transforming them into distributions that are easier to handle. The potential of this approach…
Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms
Vincent Plassier, Alain Durmus, Eric Moulines
This paper focuses on Bayesian inference in a federated learning context (FL). While several distributed MCMC algorithms have been proposed, few consider the specific limitations o…
Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo
Maxence Noble, Valentin De Bortoli, Alain Durmus
In this paper, we propose Barrier Hamiltonian Monte Carlo (BHMC), a version of the HMC algorithm which aims at sampling from a Gibbs distribution on a manifold , en…
Variational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical study
Tom Huix, Szymon Majewski, Alain Durmus +2
This paper studies the Variational Inference (VI) used for training Bayesian Neural Networks (BNN) in the overparameterized regime, i.e., when the number of neurons tends to infini…
Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation
Alain Durmus, Eric Moulines, Alexey Naumov +1
This paper provides a finite-time analysis of linear stochastic approximation (LSA) algorithms with fixed step size, a core method in statistics and machine learning. LSA is used t…
On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent
Rémi Laumont, Valentin de Bortoli, Andrés Almansa +3
Bayesian methods to solve imaging inverse problems usually combine an explicit data likelihood function with a prior distribution that explicitly models expected properties of the…
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…
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…
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…
Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections
Kimia Nadjahi, Alain Durmus, Pierre E. Jacob +2
The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant computational…
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,…
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…
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…
Convergence Analysis of Riemannian Stochastic Approximation Schemes
Alain Durmus, Pablo Jiménez, Éric Moulines +2
This paper analyzes the convergence for a large class of Riemannian stochastic approximation (SA) schemes, which aim at tackling stochastic optimization problems. In particular, th…