Erwan Le Pennec
- École polytechnique
- CMAP / Département de Mathématiques Appliquées
- 91128 Palaiseau Cedex, FRANCE
- Email :
- Office: 00.20.31
- Phone: (+33) 1 69 33 45 74
I've been an Associate Professor
(Professeur associé) at
Applied Math department
polytechnique since September 2013. I've been doing my research at
the CMAP of
École polytechnique. I'm the cohead of the
team (Signal IMage numerical ProbAbilities Statistical
Learning). I'm also the head of the "Data Scientist" chair of
École polytechnique created in octobre 2014 by École polytechnique,
Keyrus, Orange and Thales, and supported by Fondation de
l'X. This chair is dedicated to the Data Sciences training programs.
I've done a Signal Processing PhD
Mallat at the centre
de mathématiques appliquées de l'École
polytechnique. The subject of the thesis is the
introduction of geometry in image representation.
I defended it on December the 19th
2002 : its title is Bandelettes et représentations
géométriques des images (Bandelets and geometric
representation of images). In 2002-2004, I worked as a
"post-doc" in a joint-project between
Let It Wave, a company created by
Christophe Bernard, Jérôme Kalifa and myself to exploit our research on
bandelets. I consulted for the company till its closure in 2012
(even after its acquisition by Zoran and then by CSR).
From 2004 to 2010,
a "Maitre de Conférence"
(Assistant Professor) at the university Paris Diderot (Paris
7) in the
Probabilités et Modèles Aléatoires"
(Statistics team). From 2010 to 2013, I was a "Chargé de Recherche" (Research Associate)
project SELECT of Inria Saclay,
a project in which I had already worked in 2009-2010.
I defended my HdR (Habilitation à Diriger des Recherches) entitled "Some
(statistical) applications of Ockham's principle" the
19th of march 2013.
My main publications are :
Estimation in the Nonparametric Random Coefficients Binary Choice
Model by Needlet Thresholding" with E. Gautier, accepted
for publication in EJS (2017).
- "Mixture of Gaussian regressions model with logistic weights, a penalized maximum likelihood approach"
with L. Montuelle, published in EJS (2014) (DOI:10.1214/14-EJS939).
- "Partition-Based Conditional Density
Estimation" with S. Cohen, published in ESAIM P&S (2013)
- "Radon needlet
thresholding" with G. Kerkyacharian et D. Picard, published in
- "Bandlet Image
Estimation with Model Selection" with
Ch. Dossal and S. Mallat, published in Signal Processing (2011)
- "Adaptive Dantizg density
estimation" with K. Bertin et V. Rivoirard,
published in the Annales de l'IHP,
Probability and Statistics (2011)
- "Inversion of noisy Radon transform
by SVD based needlets" with
G. Kerkyacharian, G. Kyriasis, P. Petrushev and D. Picard,
published in ACHA (2010)
- "Thresholding methods to estimate the copula
F. Autin and K. Tribouley, published in JMVA (2010)
- "Maxisets for
Model Selection" with F. Autin,
J.-M. Loubes and V. Rivoirard, published in
Constructive Approximation (2010)
- "Sparse Geometrical Image Approximation
with Bandelets" , with
S. Mallat, published in IEEE Transaction on Image Processing
- "Bandelet Image Approximation and
Compression" with S. Mallat, published in SIAM
My last preprints are :
The full list, and most of the corresponding papers, is available from
Students and former students