488 citations · 3k across the 119 of their papers we have counts for
11 papers · 1 filter
AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks
Louis Leconte, Sholom Schechtman, Eric Moulines
In this paper, we develop a new algorithm, Annealed Skewed SGD - AskewSGD - for training deep neural networks (DNNs) with quantized weights. First, we formulate the training of qua…
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…
Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello +6
We consider reinforcement learning in an environment modeled by an episodic, finite, stage-dependent Markov decision process of horizon with states, and actions. The pe…
Particle-based, rapid incremental smoother meets particle Gibbs
Gabriel Cardoso, Eric Moulines, Jimmy Olsson
The particle-based, rapid incremental smoother (PARIS) is a sequential Monte Carlo technique allowing for efficient online approximation of expectations of additive functionals und…
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…
BR-SNIS: Bias Reduced Self-Normalized Importance Sampling
Gabriel Cardoso, Sergey Samsonov, Achille Thin +2
Importance Sampling (IS) is a method for approximating expectations under a target distribution using independent samples from a proposal distribution and the associated importance…
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…
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses
Daniil Tiapkin, Denis Belomestny, Eric Moulines +5
We propose the Bayes-UCBVI algorithm for reinforcement learning in tabular, stage-dependent, episodic Markov decision process: a natural extension of the Bayes-UCB algorithm by Kau…
FedPop: A Bayesian Approach for Personalised Federated Learning
Nikita Kotelevskii, Maxime Vono, Eric Moulines +1
Personalised federated learning (FL) aims at collaboratively learning a machine learning model taylored for each client. Albeit promising advances have been made in this direction,…
Diffusion bridges vector quantized Variational AutoEncoders
Max Cohen, Guillaume Quispe, Sylvain Le Corff +2
Vector Quantized-Variational AutoEncoders (VQ-VAE) are generative models based on discrete latent representations of the data, where inputs are mapped to a finite set of learned em…
On the geometric convergence for MALA under verifiable conditions
Alain Durmus, Éric Moulines
While the Metropolis Adjusted Langevin Algorithm (MALA) is a popular and widely used Markov chain Monte Carlo method, very few papers derive conditions that ensure its convergence.…