Matthieu Lerasle
Centre national de la recherche scientifique
Annales De L Institut Henri Poincare-probabilites Et Statistiques | 2012
Matthieu Lerasle
We build penalized least-squares estimators using the slope heuristic and resampling penalties. We prove oracle inequalities for the selected estimator with leading constant asymptotically equal to
Annals of Statistics | 2016
Luc Devroye; Matthieu Lerasle; Gábor Lugosi; Roberto Imbuzeiro Oliveira
1
Annals of Statistics | 2011
Matthieu Lerasle
. We compare the practical performances of these methods in a short simulation study.
Annals of Statistics | 2012
Matthieu Lerasle
We discuss the possibilities and limitations of estimating the mean of a real-valued random variable from independent and identically distributed observations from a non-asymptotic point of view. In particular, we define estimators with a sub-Gaussian behavior even for certain heavy-tailed distributions. We also prove various impossibility results for mean estimators.
Bernoulli | 2016
Matthieu Lerasle; Daniel Yasumasa Takahashi
We propose a block-resampling penalization method for marginal density estimation with nonnecessary independent observations. When the data are
Electronic Journal of Statistics | 2011
Matthieu Lerasle; Daniel Yasumasa Takahashi
beta
Annals of Applied Probability | 2017
Raphael Chetrite; Roland Diel; Matthieu Lerasle
or
arXiv: Statistics Theory | 2016
Matthieu Lerasle; Nelo Molter Magalhães; Patricia Reynaud-Bouret
tau
international conference on high performance computing and simulation | 2016
Alexandre Muzy; Matthieu Lerasle; Franck Grammont; Van Toan Dao; David R. C. Hill
-mixing, the selected estimator satisfies oracle inequalities with leading constant asymptotically equal to 1. We also prove in this setting the slope heuristic, which is a data-driven method to optimize the leading constant in the penalty.
Annals of Statistics | 2016
Magalie Fromont; Matthieu Lerasle; Patricia Reynaud-Bouret
We build penalized least-squares estimators of the marginal density of a stationary process, using the slope algorithm and resampling penalties. When the data are