arXiv subjects

Yves F. Atchade

Publications and source records attributed to Yves F. Atchade.

6 recordsLinked to original sources

arXiv2016

On perturbed proximal gradient algorithms

We study a version of the proximal gradient algorithm for which the gradient is intractable and is approximated by Monte Carlo methods (and in particular Markov Chain Monte Carlo). We derive conditions on the step size and the Monte Carlo batch size under which convergence is guaranteed: both increasing batch size and constant batch size are considered. We also derive non-asymptotic bounds for an averaged version. Our results cover both the cases of biased and unbiased Monte Carlo approximation. To support our findings, we discuss the inference of a sparse generalized linear model with random effect and the problem of learning the edge structure and parameters of sparse undirected graphical models.

math.ST↗

arXiv2011

Estimation of Network structures from partially observed Markov random fields

We consider the estimation of high-dimensional network structures from partially observed Markov random field data using a penalized pseudo-likelihood approach. We fit a misspecified model obtained by ignoring the missing data problem. We study the consistency of the estimator and derive a bound on its rate of convergence. The results obtained relate the rate of convergence of the estimator to the extent of the missing data problem. We report some simulation results that empirically validate some of the theoretical findings.

math.ST↗

arXiv2011

Limit Theorems for quadratic forms of Markov Chains

We develop a martingale approximation approach to studying the limiting behavior of quadratic forms of Markov chains. We use the technique to examine the asymptotic behavior of lag-window estimators in time series and we apply the results to Markov Chain Monte Carlo simulation. As another illustration, we use the method to derive a central limit theorem for U-statistics with varying kernels.

math.PR↗

arXiv2009

Limit theorems for some adaptive MCMC algorithms with subgeometric kernels: Part II

We prove a central limit theorem for a general class of adaptive Markov Chain Monte Carlo algorithms driven by sub-geometrically ergodic Markov kernels. We discuss in detail the special case of stochastic approximation. We use the result to analyze the asymptotic behavior of an adaptive version of the Metropolis Adjusted Langevin algorithm with a heavy tailed target density.

math.PR↗

arXiv2009

A strong law of large numbers for martingale arrays

We prove a martingale triangular array generalization of the Chow-Birnbaum-Marshall's inequality. The result is used to derive a strong law of large numbers for martingale triangular arrays whose rows are asymptotically stable in a certain sense. To illustrate, we derive a simple proof, based on martingale arguments, of the consistency of kernel regression with dependent data. Another application can be found in \cite{atchadeetfort08} where the new inequality is used to prove a strong law of large numbers for adaptive Markov Chain Monte Carlo methods.

math.PR↗

arXiv2006

Resampling from the past to improve on MCMC algorithms

We introduce the idea that resampling from past observations in a Markov Chain Monte Carlo sampler can fasten convergence. We prove that proper resampling from the past does not disturb the limit distribution of the algorithm. We illustrate the method with two examples. The first on a Bayesian analysis of stochastic volatility models and the other on Bayesian phylogeny reconstruction.

math.ST↗