Antoine

Godichon-Baggioni

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

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 Lu, W.: Online stochastic Newton methods for estimating the geometric median and applications, Hal

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

[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, à paraître dans Statistics, Hal

[12] Godichon-Baggioni, A., Werge, N. and Wintenberger, O. (2023): Non Asymptotic Analysis of Stochastic Approximation Algorithms for Streaming Data, ESAIM PS,  Hal, 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 PS,  Arxiv, 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.461–480, Arxiv, 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.591–614, Arxiv, 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:


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