Research

NAVARRO Fabien

Assistant Professor of Statistics Research interests
  • Nonparametric statistics
  • High-dimensional statistics
  • Wavelet-based methods
  • Sparsity
  • Inverse problems
  • Machine learning
  • Signal and image processing
  • Graph signal processing
Bureau 253 Téléphone +33 (0)2 99 05 32 41 Email fabien.navarro@ensai.fr Adresse ENSAI
Campus de Ker Lann
51 Rue Blaise Pascal
BP 37203
35172 BRUZ Cedex

Preprints

  • B. de Loynes, F. Navarro, B. Olivier.
    LocLets: Localized Graph Wavelets for Processing Frequency Sparse Signals on Graphs. [arXiv]
  • B. de Loynes, F. Navarro, B. Olivier.
    Data-driven thresholding in denoising with spectral graph wavelet transform. [arXiv]
  • A. Saumard, F. Navarro.
    Finite sample improvement of Akaike's Information Criterion.[nbsp][arXiv]
  • C. Chesneau, S. El Kolei, F. Navarro.
    Parametric estimation of hidden Markov models by least squares type estimation and deconvolution.[Hal]

Book Translation

Journal Articles

  • F. Navarro, A. Saumard.
    Slope heuristics and V-Fold model selection in heteroscedastic regression using strongly localized bases
    ESAIM: Probability and Statistics
    , Vol. 21, 2017. [arXiv][Journal][matlab code]
  • C. Chesneau and F. Navarro.
    On the pointwise mean squared error of a multidimensional term-by-term thresholding wavelet estimator
    Communications in Statistics - Theory and Methods, Vol. 46(11), 2017. [Hal][Journal]
  • C. Chesneau, F. Navarro , O.S. Serea.
    A note on the adaptive estimation of the differential entropy by wavelet methods
    Comment.Math.Univ.Carolin., Vol. 58(1), 2017. [Hal]
  • Y. P. Chaubey, C. Chesneau, F. Navarro.
    Linear wavelet estimation of the derivatives of a regression function based on biased data
    Communications in Statistics - Theory and Methods, Vol. 46(19), 2017. [Hal][Journal]
  • I. Bulla, C. Chesneau, F. Navarro , T. Mark.
    A note on the adaptive estimation of a bi-dimensional density in the case of knowledge of the copula density
    Statistics and Probability Letters, Vol. 105, 2015. [Hal][Journal]
  • F. Navarro, C. Chesneau, J. Fadili.
    On adaptive wavelet estimation of a class of weighted densities
    Communications in Statistics - Simulation and Computation, Vol. 44(8), 2015. [Hal][Journal]
  • C. Chesneau, M. Kachour, F. Navarro.
    Average Derivative Estimation from Biased Data
    ISRN Probability and Statistics, Vol. 2014, Article ID 864530, 7 pages, 2014. [Journal]
  • C. Chesneau, F. Navarro.
    On a plug-in wavelet estimator for convolutions of densities
    Journal of Statistical Theory and Practice, Vol. 8(4), 2014. [Hal][Journal]
  • C. Chesneau, M. Kachour, F. Navarro.
    On the estimation of density-weighted average derivative by wavelet methods under various dependence structures
    Sankhya, Vol. 76(1), pp 48–76, 2014. [Hal][Journal]
  • C. Chesneau, F. Comte, F. Navarro.
    Fast nonparametric estimation for convolutions of densities
    The Canadian Journal of Statistics,Vol. 41(4), pp. 617–636, 2013. [Hal][Journal]
  • C. Chesneau, M. Kachour, F. Navarro.
    A note on the adaptive estimation of a quadratic functional from dependent observations
    İSTATİSTİK, Vol. 6(1), pp. 10–26, 2013. [Hal][Journal]
  • F. Navarro, C. Chesneau, J. Fadili, T. Sassi.
    Block thresholding for wavelet-based estimation of function derivatives from a heteroscedastic multichannel convolution model
    Electronic Journal of Statistics, Vol. 7, pp. 428–453, 2013. [Hal][Journal]

Proceedings of international conferences

  • C. Chesneau, J. Kou, F. Navarro.
    Linear wavelet estimation in regression with additive and multiplicative noise.
    [nbsp]to appear in[nbsp]ISNPS 2018.[Hal]
  • F. Navarro, A. Saumard.
    Efficiency of the V -fold model selection for localized bases
    ISNPS 2016. Springer Proceedings in Mathematics [&] Statistics, vol 250. Springer, Cham, 2018.[Hal][Proc][matlab code]
  • F. Navarro, J. Fadili, C. Chesneau.
    Adaptive parameter selection for block wavelet-thresholding deconvolution
    11th IFAC International Workshop on Adaptation and Learning in Control and Signal Processing, 2013. [Hal][Proc]

Proceedings of national conferences

  • A. Saumard, F. Navarro.
    Une sur-pénalisation théoriquement fondée du critère AIC
    49èmes Journées de Statistique de la SFdS, Avignon, 2017.[Hal]
  • F. Navarro, A. Saumard.
    Sélection optimale de modèles à base localisée en régression hétéroscédastique
    48èmes Journées de Statistique de la SFdS, Montpellier, 2016.[Hal]

Ph.D.

  • Estimateurs adaptatifs avec parcimonie structurée, 2013. [Hal]

2017-2018 ENSAI

  • CM+TP 3ème année MKT et SID,[nbsp]Support Vector Machine
  • CM+TP MSc Statistics for Smart data,[nbsp]Machine learning: Features Selection [&] Regularization Methods
  • CM+TP 3ème année GS,[nbsp]Python
  • CM+TP 3ème année GS et SV,[nbsp]Modélisation non-linéaire
  • TP 1ère année,[nbsp]Statistiques avec R
2016-2017 ENSAI
  • CM+TP MSc Big data, Penalized Regression
  • CM+TP 3ème année GS, Python
  • CM+TP 3ème année GS et SV, Modélisation non-linéaire
  • TP 1ère année, Statistiques avec R

2015-2016 ENSAI

  • CM+TP 3ème année GS et SV, Modélisation non-linéaire
  • TD+TP 2ème année, Statistique computationnelle
  • TP 1ère année, Statistiques avec R
  • TD 1ère année, Algèbre

2014-2015 Université de Concordia (Fall and Winter)

  • CM Undergraduate, Fundamental Mathematics II (MATH209)Ch3   Ch4   Ch5   Ch6

2013-2014 Université de Nantes

  • CM+TD L1 MIPC - Polytech Nantes, Mathématiques
  • TD L2 Physique, Probabilité pour la Physique
  • TD L3 Maths-Eco, Inférence statistique
  • TD+TP L2 Maths, Probabilités discrètes

2012-2013 Université de Caen

  • TD L2 SEG, Mathématiques pour économistes
  • TD L1 Biologie, Mathématiques

2011-2012 Université de Caen

  • TP M1 Ingénierie Mathématiques et Mécanique, Optimisation
  • TD+TP L3 MASS-Maths, Optimisation
  • TP L2 MASS, Optimisation

R package : rwavelet

see package vignette for more details.

 


 

Matlab toolbox to perform Optimal model selection in heteroscedastic regression

F. Navarro and A. Saumard.
Slope heuristics and V-Fold model selection in heteroscedastic regression using strongly localized bases
ESAIM: Probability and Statistics
, Vol. 21, 2017. [arXiv][doi][code]

 


 

Matlab toolbox to perform V-fold model selection for localized bases

F. Navarro and A. Saumard.
Efficiency of the V -fold model selection for localized bases
soumis
,2017.[Hal][code]