Antoine

Godichon-Baggioni


Maître de Conférences (HdR) à Sorbonne Université
Laboratoire de Probabilités, Statistique et Modélisation (LPSM)
UFR de Mathématiques
4 Place Jussieu -- Tour 15-25 -- Bureau 222
75005 Paris
Mail: antoine"dot"godichon_baggioni"at"upmc"dot"fr

Accueil Enseignements Recherche Etudiants
Curriculum vitae


Thèmes de recherche:  Statistique Robuste, Algorithmes stochastiques, Descentes de gradient, Médiane géométrique, Classification, Algorithmes de Newton stochastiques


Articles soumis:


Godichon-Baggioni, A., Robin, S., and Sansonnet, L.: Online and Offline Robust Multivariate Linear Regression, Hal,

Godichon-Baggioni, A., Lu, W. and Portier, B.:  A Full Adagrad algorithm with O(Nd) operations, Hal,

Surendran, S., Fermanin, A., Godichon-Baggioni, A. and Le Corff, S.: Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation, Hal

Godichon-Baggioni, A., Lu, W. and Portier, B.: Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms, Hal

Godichon-Baggioni, A., Nguyen, D. and Tran M.-N.: Natural gradient Variational Bayes without matrix inversion, Arxiv

Godichon-Baggioni, A. and Werge, N. : On Adaptive Stochastic Optimization for Streaming Data: A Newton's Method with O(dN) Operations, Hal

Brazey, D., Godichon-Baggioni, A. and  Portier, B.A mixture of ellipsoidal densities for 3D data modelling, Hal

Godichon-Baggioni, A. and Tarrago, P.: Non asymptotic analysis of Adaptive stochastic gradient algorithms and applications, Hal


Articles acceptés:


[19] Godichon-Baggioni, A. and Lu, W.: Online stochastic Newton methods for estimating the geometric median and applications, Journal of Multivariate Analysis, Hal, Journal

[18] Godichon-Baggioni, A. and Surendran, S. (2024): A penalized criterion for selecting the number of clusters for K-medians, Journal of Computational and Graphical Statistics, Hal, Journal, Package R Kmedians, codes

[17] Godichon-Baggioni and Robin, S. (2023): A robust model-based clustering based on the geometric median and the Median Covariation Matrix, Statistics and Computing, Hal, Journal, Package R RGMM

[16] Godichon-Baggioni, A., Lu, W. and Portier, B. (2023): Recursive ridge regression using second-order stochastic algorithms, Computational Statistics and Data Analysis, Hal, Journal

[15] Godichon-Baggioni, A., Werge, N. and Wintenberger, O. (2023): Learning from time-dependent streaming data with online stochastic algorithms, Transactions on Machine Leaning Research, Journal, Hal

[14] Cénac, P., Godichon-Baggioni, A. and  Portier, B. (2023): An efficient Averaged Stochastic Gauss-Newtwon algorithm for estimating parameters of non linear regressions models, à paraître dans Bernoulli, Arxiv

[13] Godichon-Baggioni, A. (2023):  Convergence in quadratic mean of averaged stochastic gradient algorithms without strong convexity nor bounded gradient, Statistics, Hal, Journal

[12] Godichon-Baggioni, A., Werge, N. and Wintenberger, O. (2023): Non Asymptotic Analysis of Stochastic Approximation Algorithms for Streaming Data, ESAIM PSHal, Journal

[11] Boyer, C. and Godichon-Baggioni, A. (2022): On the asymptotic rate of convergence of Stochastic Newton algorithms and their Weighted Averaged versions, Computational Optimization and Applications Hal, Codes, Journal

[10] Godichon-Baggioni, A. and Saadane, S. (2020): On the rates of convergence of Parallelized Averaged Stochastic Gradient Algorithms, Statistics, Arxiv, Journal

[9] Bercu, B., Godichon-Baggioni, A., Portier, B. (2020): An efficient stochastic Newton algorithm for parameter estimation in logistic regressions, SIAM, Journal on Control and Optimization, Arxiv, Journal

[8] Godichon-Baggioni, A., Maugis-Rabusseau, C., Rau, A. (2020): Multi-view cluster agregation and splitting with an application to multi-omic breast cancer data, Annals of Applied Statistics, HAL, Journal, Package R maskmeans

[7] Godichon-Baggioni, A. (2019): Lp and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective, ESAIM PSArxiv, Journal, Erratum

[6] Godichon-Baggioni, A. (2019): Online estimation of the asymptotic variance for averaged stochastic gradient algorithms, Journal of Statistical Planning and Inference, Arxiv, Journal

[5] Godichon-Baggioni, A., Maugis-Rabusseau, C. and Rau, A. (2018): Clustering transformed compositional data using K-means, with applications in gene expression and bicyle sharing system data, Journal of Applied Statistics, Arxiv, Journal, Package R coseq

[4] Godichon-Baggioni, A. and Portier, B. (2017): An averaged projected Robbins-Monro algorithm for estimating the parameters of a truncated spherical distribution, Electronic Journal of Statistics, vol. 11, p. 1890-1927 , Arxiv, Journal

[3] Cardot, H., Godichon-Baggioni, A. (2017): Fast Estimation of the Median Covariation Matrix with Application to Online Robust Principal Components Analysis,  TEST, vol 26, p.461–480Arxiv, Journal

[2] Cardot, H., Cénac, P., Godichon-Baggioni, A. (2017): Online estimation of the geometric median in Hilbert spaces : non asymptotic confidence balls, The Annals of Statistics, vol 45, p.591–614Arxiv, Journal

[1] Godichon-Baggioni, A. (2016):  Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms : Lp and almost sure rates of convergence, Journal of Multivariate Analysis, vol. 146, p. 209.222., Arxiv, Journal



Contributions à des packages R:


RobRegression, disponible sur le CRAN, with S. Robin and  L. Sansonnet

Kmedians, disponible sur le CRAN, avec S. Surendran

RGMM, disposnible sur le CRAN, avec S. Robin

Maskmeans, disponible sur Github, avec C. Maugis-Rabusseau et A. Rau

coseq, disponible sur Bioconductor, avec C. Maugis-Rabusseau et A. Rau



Autres:


Habilitation à Diriger des Recherches, soutenue le 14 mars 2023: Online stochastic algorithms and applications, PDF

Thèse soutenue le 17 Juin 2016:
Algorithmes stochastiques pour la statistique robuste en grande dimension, sous la direction de Hervé Cardot et Peggy Cénac, PDF