Search Results for author: Eric Moulines

Found 37 papers, 4 papers with code

Fast and Consistent Learning of Hidden Markov Models by Incorporating Non-Consecutive Correlations

no code implementations ICML 2020 Robert Mattila, Cristian Rojas, Eric Moulines, Vikram Krishnamurthy, Bo Wahlberg

Can the parameters of a hidden Markov model (HMM) be estimated from a single sweep through the observations -- and additionally, without being trapped at a local optimum in the likelihood surface?

Time Series

From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses

no code implementations16 May 2022 Daniil Tiapkin, Denis Belomestny, Eric Moulines, Alexey Naumov, Sergey Samsonov, Yunhao Tang, Michal Valko, Pierre Menard

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 Kaufmann et al. (2012) for multi-armed bandits.

Multi-Armed Bandits

Diffusion bridges vector quantized Variational AutoEncoders

no code implementations10 Feb 2022 Max Cohen, Guillaume Quispe, Sylvain Le Corff, Charles Ollion, Eric Moulines

In this work, we propose a new model to train the prior and the encoder/decoder networks simultaneously.

NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform

1 code implementation NeurIPS 2021 Achille Thin, Yazid Janati El Idrissi, Sylvain Le Corff, Charles Ollion, Eric Moulines, Arnaud Doucet, Alain Durmus, Christian Robert

Sampling from a complex distribution $\pi$ and approximating its intractable normalizing constant $\mathrm{Z}$ are challenging problems.

Ex$^2$MCMC: Sampling through Exploration Exploitation

no code implementations4 Nov 2021 Evgeny Lagutin, Daniil Selikhanovych, Achille Thin, Sergey Samsonov, Alexey Naumov, Denis Belomestny, Maxim Panov, Eric Moulines

We develop an Explore-Exploit Markov chain Monte Carlo algorithm ($\operatorname{Ex^2MCMC}$) that combines multiple global proposals and local moves.

Monte Carlo Variational Auto-Encoders

1 code implementation30 Jun 2021 Achille Thin, Nikita Kotelevskii, Arnaud Doucet, Alain Durmus, Eric Moulines, Maxim Panov

Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO).

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

no code implementations11 Jun 2021 Vincent Plassier, Maxime Vono, Alain Durmus, Eric Moulines

Performing reliable Bayesian inference on a big data scale is becoming a keystone in the modern era of machine learning.

Bayesian Inference

Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize

no code implementations NeurIPS 2021 Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov, Kevin Scaman, Hoi-To Wai

This family of methods arises in many machine learning tasks and is used to obtain approximate solutions of a linear system $\bar{A}\theta = \bar{b}$ for which $\bar{A}$ and $\bar{b}$ can only be accessed through random estimates $\{({\bf A}_n, {\bf b}_n): n \in \mathbb{N}^*\}$.

QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning

no code implementations1 Jun 2021 Maxime Vono, Vincent Plassier, Alain Durmus, Aymeric Dieuleveut, Eric Moulines

The objective of Federated Learning (FL) is to perform statistical inference for data which are decentralised and stored locally on networked clients.

Federated Learning

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

no code implementations25 May 2021 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 iteration.

NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform

1 code implementation17 Mar 2021 Achille Thin, Yazid Janati, Sylvain Le Corff, Charles Ollion, Arnaud Doucet, Alain Durmus, Eric Moulines, Christian Robert

Sampling from a complex distribution $\pi$ and approximating its intractable normalizing constant Z are challenging problems.

Rates of convergence for density estimation with GANs

no code implementations30 Jan 2021 Denis Belomestny, Eric Moulines, Alexey Naumov, Nikita Puchkin, Sergey Samsonov

In this work we undertake a thorough study of the non-asymptotic properties of the vanilla generative adversarial networks (GANs).

Density Estimation

MISSO: Minimization by Incremental Stochastic Surrogate Optimization for Large Scale Nonconvex and Nonsmooth Problems

no code implementations1 Jan 2021 Belhal Karimi, Hoi To Wai, Eric Moulines, Ping Li

Many constrained, nonconvex and nonsmooth optimization problems can be tackled using the majorization-minimization (MM) method which alternates between constructing a surrogate function which upper bounds the objective function, and then minimizing this surrogate.

Variational Inference

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

no code implementations31 Dec 2020 Achille Thin, Nikita Kotelevskii, Christophe Andrieu, Alain Durmus, Eric Moulines, Maxim Panov

This paper fills the gap by developing general tools to ensure that a class of nonreversible Markov kernels, possibly relying on complex transforms, has the desired invariance property and leads to convergent algorithms.

A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm

no code implementations NeurIPS 2020 Gersende Fort, Eric Moulines, Hoi-To Wai

The Expectation Maximization (EM) algorithm is of key importance for inference in latent variable models including mixture of regressors and experts, missing observations.

A Stochastic Path-Integrated Differential EstimatoR Expectation Maximization Algorithm

no code implementations30 Nov 2020 Gersende Fort, Eric Moulines, Hoi-To Wai

The Expectation Maximization (EM) algorithm is of key importance for inference in latent variable models including mixture of regressors and experts, missing observations.

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

no code implementations24 Nov 2020 Gersende Fort, Eric Moulines, Hoi-To Wai

The Expectation Maximization (EM) algorithm is a key reference for inference in latent variable models; unfortunately, its computational cost is prohibitive in the large scale learning setting.

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

no code implementations4 Feb 2020 Maxim Kaledin, Eric Moulines, Alexey Naumov, Vladislav Tadic, Hoi-To Wai

Our bounds show that there is no discrepancy in the convergence rate between Markovian and martingale noise, only the constants are affected by the mixing time of the Markov chain.

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

no code implementations NeurIPS 2019 Belhal Karimi, Hoi-To Wai, Eric Moulines, Marc Lavielle

To alleviate this problem, Neal and Hinton have proposed an incremental version of the EM (iEM) in which at each iteration the conditional expectation of the latent data (E-step) is updated only for a mini-batch of observations.

Non-asymptotic Analysis of Biased Stochastic Approximation Scheme

no code implementations2 Feb 2019 Belhal Karimi, Blazej Miasojedow, Eric Moulines, Hoi-To Wai

We illustrate these settings with the online EM algorithm and the policy-gradient method for average reward maximization in reinforcement learning.

reinforcement-learning

The promises and pitfalls of Stochastic Gradient Langevin Dynamics

no code implementations NeurIPS 2018 Nicolas Brosse, Alain Durmus, Eric Moulines

As $N$ becomes large, we show that the SGLD algorithm has an invariant probability measure which significantly departs from the target posterior and behaves like Stochastic Gradient Descent (SGD).

Decentralized Frank-Wolfe Algorithm for Convex and Non-convex Problems

no code implementations5 Dec 2016 Hoi-To Wai, Jean Lafond, Anna Scaglione, Eric Moulines

The convergence of the proposed algorithm is studied by viewing the decentralized algorithm as an inexact FW algorithm.

Matrix Completion Sparse Learning

Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo

no code implementations NeurIPS 2016 Alain Durmus, Umut Simsekli, Eric Moulines, Roland Badeau, Gaël Richard

We illustrate our framework on the popular Stochastic Gradient Langevin Dynamics (SGLD) algorithm and propose a novel SG-MCMC algorithm referred to as Stochastic Gradient Richardson-Romberg Langevin Dynamics (SGRRLD).

Bayesian Inference

High-dimensional Bayesian inference via the Unadjusted Langevin Algorithm

no code implementations5 May 2016 Alain Durmus, Eric Moulines

We consider in this paper the problem of sampling a high-dimensional probability distribution $\pi$ having a density with respect to the Lebesgue measure on $\mathbb{R}^d$, known up to a normalization constant $x \mapsto \pi(x)= \mathrm{e}^{-U(x)}/\int_{\mathbb{R}^d} \mathrm{e}^{-U(y)} \mathrm{d} y$.

Bayesian Inference

On the Online Frank-Wolfe Algorithms for Convex and Non-convex Optimizations

no code implementations5 Oct 2015 Jean Lafond, Hoi-To Wai, Eric Moulines

With a strongly convex stochastic cost and when the optimal solution lies in the interior of the constraint set or the constraint set is a polytope, the regret bound and anytime optimality are shown to be ${\cal O}( \log^3 T / T )$ and ${\cal O}( \log^2 T / T)$, respectively, where $T$ is the number of rounds played.

Adaptive Multinomial Matrix Completion

no code implementations26 Aug 2014 Olga Klopp, Jean Lafond, Eric Moulines, Joseph Salmon

The task of estimating a matrix given a sample of observed entries is known as the \emph{matrix completion problem}.

Matrix Completion Multi-class Classification +1

Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)

no code implementations NeurIPS 2013 Francis Bach, Eric Moulines

We consider the stochastic approximation problem where a convex function has to be minimized, given only the knowledge of unbiased estimates of its gradients at certain points, a framework which includes machine learning methods based on the minimization of the empirical risk.

Adaptive parallel tempering algorithm

2 code implementations4 May 2012 Blazej Miasojedow, Eric Moulines, Matti Vihola

Parallel tempering is a generic Markov chain Monte Carlo sampling method which allows good mixing with multimodal target distributions, where conventional Metropolis-Hastings algorithms often fail.

Computation

Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning

no code implementations NeurIPS 2011 Eric Moulines, Francis R. Bach

We consider the minimization of a convex objective function defined on a Hilbert space, which is only available through unbiased estimates of its gradients.

Kernel Change-point Analysis

no code implementations NeurIPS 2008 Zaïd Harchaoui, Eric Moulines, Francis R. Bach

Change-point analysis of an (unlabelled) sample of observations consists in, first, testing whether a change in the distribution occurs within the sample, and second, if a change occurs, estimating the change-point instant after which the distribution of the observations switches from one distribution to another different distribution.

Two-sample testing

Online EM Algorithm for Latent Data Models

no code implementations27 Dec 2007 Olivier Cappé, Eric Moulines

The resulting algorithm is usually simpler and is shown to achieve convergence to the stationary points of the Kullback-Leibler divergence between the marginal distribution of the observation and the model distribution at the optimal rate, i. e., that of the maximum likelihood estimator.

Cannot find the paper you are looking for? You can Submit a new open access paper.