Ill-posed linear inverse problems that combine knowledge of the forward
...
We provide a rigorous analysis of training by variational inference (VI)...
Federated Learning (FL) is a machine learning framework where many clien...
Energy-based models (EBMs) are versatile density estimation models that
...
Reinforcement learning (RL) allows an agent interacting sequentially wit...
We consider the problem of learning in a non-stationary reinforcement
le...
We consider the problem of minimizing a non-convex function over a smoot...
We consider the reinforcement learning (RL) setting, in which the agent ...
In this paper, we establish novel deviation bounds for additive function...
Stochastic approximation (SA) is a classical algorithm that has had sinc...
Transport maps can ease the sampling of distributions with non-trivial
g...
Non-linear state-space models, also known as general hidden Markov model...
This paper introduces a novel algorithm, the Perturbed Proximal
Precondi...
In this paper, we develop a new algorithm, Annealed Skewed SGD - AskewSG...
This paper focuses on Bayesian inference in a federated learning context...
We consider reinforcement learning in an environment modeled by an episo...
The particle-based, rapid incremental smoother (PARIS) is a sequential M...
Importance Sampling (IS) is a method for approximating expectations unde...
This paper provides a finite-time analysis of linear stochastic approxim...
This paper studies the Variational Inference (VI) used for training Baye...
Personalised federated learning (FL) aims at collaboratively learning a
...
We propose the Bayes-UCBVI algorithm for reinforcement learning in tabul...
While the Metropolis Adjusted Langevin Algorithm (MALA) is a popular and...
We develop an Explore-Exploit Markov chain Monte Carlo algorithm
(Ex^2MC...
The Expectation Maximization (EM) algorithm is the default algorithm for...
We study the convergence in total variation and V-norm of discretization...
Variational auto-encoders (VAE) are popular deep latent variable models ...
Performing reliable Bayesian inference on a big data scale is becoming a...
This paper provides a non-asymptotic analysis of linear stochastic
appro...
Federated learning aims at conducting inference when data are decentrali...
Incremental Expectation Maximization (EM) algorithms were introduced to
...
Simultaneously sampling from a complex distribution with intractable
nor...
This paper studies fixed step-size stochastic approximation (SA) schemes...
We undertake a precise study of the non-asymptotic properties of vanilla...
This paper studies the exponential stability of random matrix products d...
Markov Chain Monte Carlo (MCMC) is a class of algorithms to sample compl...
The Expectation Maximization (EM) algorithm is of key importance for
inf...
The Expectation Maximization (EM) algorithm is a key reference for infer...
This paper analyzes the convergence for a large class of Riemannian
stoc...
In this contribution, we propose a new computationally efficient method ...
Linear two-timescale stochastic approximation (SA) scheme is an importan...
Uncertainty quantification for deep learning is a challenging open probl...
We introduce and analyse a new family of algorithms which generalizes an...
The EM algorithm is one of the most popular algorithm for inference in l...
The ability to generate samples of the random effects from their conditi...
We state and prove a quantitative version of the bounded difference
ineq...
We consider the problem of sampling from a target distribution which is
...
Stochastic approximation (SA) is a key method used in statistical learni...
Many applications of machine learning involve the analysis of large data...
Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC
a...