Publications

Page Principale  


E. Gassiat, G. Stoltz,
The van Trees inequality in the spirit of Hajek and Le Cam
soumis, 2024.

E. Gassiat, S. Le Corff,
Variational excess risk bound for general state space models
soumis, 2023.

E. Aubinais, E. Gassiat, P. Piantanida,
Fundamental limits of membership inference attacks on machine learning models
soumis, 2023.

E. Gassiat, I. Kaddouri, Z. Naulet,
Model-based clustering using nonparametric hidden Markov models
soumis, 2023.

K. Abraham, E. Gassiat, Z. Naulet,
Frontiers to the learning of nonparametric hidden Markov models
soumis, 2023.

J. Capitao-Miniconi, E. Gassiat, L. Lehéricy,
Support and distribution inference from noisy data
soumis, 2023.

M. Chagneux, E. Gassiat, P. Cloaguen, S. Le Corff,
Amortized backward variational inference in nonlinear state-space models
Journal of Machine Learning Research, à paraitre.

J. Capitao-Miniconi, E. Gassiat,
Deconvolution of spherical data corrupted with unknown noise
Electronic Journal of Statistics (17), 1, 607-649, 2023.

K. Abraham, E. Gassiat, Z. Naulet,
Fundamental limits for learning hidden Markov model parameters
IEEE Trans. Info. th (69), 3, 1777-1794, 2023.

H. Hälvä, S. Le Corff, L. Lehéricy, J. So, Y. Zhu, E. Gassiat, A. Hyvarinen,
Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA
Advances in Neural Information Processing Systems (NeurIPS), 2021.

J. Ollion, C. Ollion, E. Gassiat, L. Lehéricy, S. Le Corff,
Joint self-supervised blind denoising and noise estimation
soumis, 2021.

K. Abraham, I. Castillo, E. Gassiat,
Multiple Testing in Nonparametric Hidden Markov Models: An Empirical Bayes Approach
Journal of Machine Learning Research (23), 1-57, 2022.

E. Gassiat, L. Lehéricy, S. Le Corff
Deconvolution with unknown noise distribution is possible for multivariate signals
Annals of Statistics, 50(1), 303-323, 2022. Version ArXiv

E. Gassiat, L. Lehéricy, S. Le Corff
Identifiability and consistent estimation of nonparametric translation hidden Markov models with general state space
Journal of Machine Learning Research, 21(115), 1-40, 2020.

E. Gassiat
Universal Coding and Order Identification by Model Selection Methods
Springer Monographs in Mathematics, 2018.

B. Auder, E. Gassiat, M.A. Loum

Least squares moment identification of binary regression mixture models
Metrika, 84(4), 561-593, 2021.

M.A. Loum, M.-A. Poursat, A. Sow, A. A. Sall, C. Loucoubar, E. Gassiat

Multinomial logistic model for coinfection diagnosis between arbovirus and malaria in Kedougou
International Journal of Biostatistics, 15 (2), 2019.

E. Gassiat

Mixtures of Nonparametric Components and Hidden Markov Models
Chapitre du livre Handbook of Mixture Analysis (ed. G. Celeux, S. Fruhwirth-Schnatter, C. Robert) CRC Press, 2019.

F. Koladjo, M. Ohannessian, E. Gassiat

A truncation model for estimating species richness
International Journal of Biostatistics, 15 (2), 2019.

A. Ben-Hamou, S. Boucheron, E. Gassiat

Pattern coding meets Censoring: (almost) Adaptive coding on countable alphabets
soumis, 2016.

E. Gassiat, J. Rousseau, E. Vernet

Efficient semiparametric estimation and model selection for multidimensional mixtures
Electronic Journal of Statistics, 18 (1), 703-740, 2018.

N. Verzelen, E. Gassiat

Adaptive estimation of High-Dimensional Signal-to-Noise Ratios
Bernoulli, 24 (4B), 3683-3710, 2018.

Y. de Castro, E. Gassiat
, S. Le Corff
Consistent estimation of the filtering and smoothing distributions in non-parametric hidden Markov models
IEEE Trans. Info. th, 63 (8), 4758-4777, 2017.

A. Bonnet,
C. Lévy-Leduc, E. Gassiat, R. Toro, T. Bourgeron
Improving heritability estimation by a variable selection approach in sparse high dimensional linear mixed models
Journal of the Royal Statistical Society Series C, 67 (4), 813-839, 2018.

Y. de Castro, E. Gassiat
, C. Lacour
Minimax adaptive estimation of non-parametric hidden Markov models
Journal of Machine Learning Research, 17, 111 (43p), 2016.

E. Gassiat
Codage universel et identification d'ordre par sélection de modèles
Cours spécialisés de la SMF, 2014.

A. Bonnet, E. Gassiat
, C. Lévy-Leduc
Heritability estimation in high dimensional linear mixed models
Electronic Journal of Statistics, 9, 2, 2099–2129, 2015.

S. Boucheron, E. Gassiat
, M. Ohannessian
About adaptive coding on countable alphabets : Max-stable envelope classes
IEEE Trans. Info. th,  61, 9, 4948–4967, 2015.

E. Gassiat, A. Cleynen, S. Robin

Inference in finite state space non parametric hidden Markov models and applications
Statistics and Computing,  26 (1-2), 61-71, 2016.

E. Gassiat, J. Rousseau

Non parametric finite translation hidden Markov models and extensions
Bernoulli,  22(1), 193-212, 2016.

E. Gassiat, J. Rousseau

About the posterior distribution in hidden Markov models with unknown number of states
Bernoulli 20 (4), 2039-2075, 2014.

E. Gassiat, R. van Handel
The local geometry of finite mixtures
Transactions of the AMS,  2, 366, 1047-1072, 2014.

D. Bontemps, S. Boucheron, E. Gassiat
About adaptive coding on countable alphabets
IEEE Trans. Info. th, 60, 2, 808-821, 2014.

E. Gassiat, R. van Handel
Consistent order estimation and minimal penalties
IEEE Trans. Info. th, 59, 2, 1115-1128, 2013.

A. Galves, A. Garivier, E. Gassiat

Joint estimation of intersecting context tree models
Scandinavian Journal of Statistics,  40, 344-362, 2013.

D. Bontemps, S. Boucheron, E. Gassiat
Adaptive compression against a countable alphabet
AofA'12, 201–218, Discrete Math. Theor. Comput. Sci. Proc., AQ, Assoc. Discrete Math. Theor. Comput. Sci., Nancy, 2012.

R. Douc, E. Gassiat, B. Landelle, E. Moulines
Forgetting of the initial distribution for non ergodic Hidden Markov Chains
Annals of Applied Probability,  20, 1638-1662, 2010.

W. Toussile, E. Gassiat
Model Based Clustering using multilocus data with loci selection
Advances in Data Analysis and Classification,  3, 109-134, 2009.

S. Boucheron, E. Gassiat

A Bernstein-von Mises Theorem for discrete probability distributions
Electronic Journal of Statistics, 3, 114-148, 2009. 

J.-M. Azais, E. Gassiat, C. Mercadier

The likelihood ratio test for general mixture models with possibly structural parameter.
ESAIM P&S, 13, 301-327, 2009.

S. Boucheron, A. Garivier, E. Gassiat
Coding on countably infinite alphabets
IEEE Trans. Info. th, 55, 358-373, 2009.

A. Chambaz, A. Garivier, E. Gassiat
A MDL approach to HMM with Poisson and Gaussian emissions. Application to order indentification.
Journal of Statistical Planning and Inference, 139, 3, 962-977, 2009.

E. Gassiat, B. Landelle
Semiparametric regression estimation using noisy nonlinear non invertible functions of the observations
soumis,  2008.

G. Mahiane, C. Legeai, D. Taljaard, A. Latouche, A. Puren, A. Peillon, J. Bretagnolle, P. Ndong Nguema, E. Gassiat, B. Auvert
Transmission probabilities of HIV and HSV-2, effect of male circumcision and interaction: a longitudinal study in a township of South Africa
AIDS, 2008.

A. Arribas-Gil, E. Gassiat, C. Matias
Parameter estimation in pair hidden Markov models.
Scandinavian Journal of Statistics, 33, 4, 651-671, 2006.

S. Boucheron, E. Gassiat
Error exponents for AR order testing.
IEEE Trans. Info. th, 52, 472--488,  2006.

J.-M. Azais, E. Gassiat, C. Mercadier
Asymptotic distribution and power of the likelihood ratio test for mixtures: bounded and unbounded case.
Bernoulli, 12, 5, 775-799, 2006.

E. Gassiat, C. Levy-Leduc

nEfficient semi-parametric estimation of the periods in a superposition of periodic functions with unknown shape.
Journal of Time Series Analysis, 27, 6, 877-910, 2006.
 
S. Boucheron,  E. Gassiat
An information-theoretic perspective on Order Estimation.
Chapter 15 "Inference in Hidden Markov Models" edited by O. Cappé and T. Ryden., Springer, 2005.
 
E. Nédélec, T. Moncion, E. Gassiat, B. Bossart, G. Duchateau-Nguyen, A. Denise, M. Termier
A pairwise alignment algorithm which favours clusters of blocks
Journal of Computational Biology, 12, 1, 2005.
 
E. Gassiat, S. Boucheron
Optimal error exponents in hidden Markov model order estimation
IEEE Trans. Info. th., 48, 964-980, 2003.
 
E. Gassiat
Likelihood ratio inequalities with applications to various mixtures
Ann. Inst.Henri Poincaré, 38, 897-906, 2002.
 
B. Bercu, E. Gassiat, E. Rio
Concentration inequalities, large and moderate deviations for self-normalized empirical processes 
Annals of Proba., 30, 1576-1604, 2002.
 
E. Gassiat, C. Kéribin
The likelihood ratio test for the number of components in a mixture with Markov regime 
ESAIM P&S, 2000.
 
I. Csiszar, F. Gamboa, E. Gassiat
M.E.M. pixel correlated solutions for generalized moment and interpolation problems 
IEEE Trans. Info. th., 45, 2253-2271, 1999.
 
E. Moulines, J.F. cardoso , E. Gassiat
Maximum likelihood for blind separation and deconvolution of noisy signals using mixture models
ICASSP 97

E. Gassiat, E. Gautherat
Speed of convergence for the blind deconvolution of a linear system with discrete random input
Annals of Stat., 27, 1999. 

D. Dacunha-Castelle, E. Gassiat
Testing the order of a model using locally conic parametrization: population mixtures and stationary ARMA processes
Annals of Stat.,  27, 4, 1178-1209, 1999.

D. Dacunha-Castelle, E. Gassiat
Testing in locally conic models and application to mixture models
 ESAIM P et S, 1, 1997.

E. Gassiat, F. Gamboa
Source Separation when the input sources are discrete or have constant modulus
IEEE Trans. Signal Processing, 45 , 1997.

E. Gassiat, E. Gautherat
Identification of noisy linear systems with discrete random input
IEEE Trans. Inf. Theory, 44, 1941-1952, 1998.

E. Gassiat
Déconvolution aveugle de systèmes linéaires discrets bruités
CRAS 319, série I, 489--492, 1994.

E. Gassiat, D. Dacunha-Castelle
Estimation of the number of components in a mixture
Bernoulli  3, 279-299, 1997.

E. Gassiat, F. Gamboa
Bayesian methods  and Maximum entropy for ill posed inverse problems
Annals of Statistics, 25,  328-350, 1997.

E. Gassiat, F. Gamboa
Blind deconvolution of discrete linear systems
Annals of Statistics, 24,  1964-1981, 1996.

E. Gassiat, F. Gamboa
Sets of superconcentration and the maximum entropy method on the mean
SIAM Journal on Mathematical Analysis, 27, 1129-1152, 1996.

E. Gassiat, F. Gamboa
The maximum entropy method on the mean : applications to linear programming and superresolution
Mathematical Programming, serie A, 66, 103--122, 1994.

 E. Gassiat
Adaptive estimation in non causal stationary AR processes
Annals of Statistics,  21, 4, 2022--2042, 1993.

 E. Gassiat, P. Doukhan
Quadratic deviation of penalized mean squares regression estimates
Journal of Mult. Analysis, 41, 89--101, 1992.

E. Gassiat, F. Monfront, Y. Goussart
On simultaneous signal estimation and parameter identification using a  generalized likelihood approach
IEEE Trans. on Inf. Theory , 38-1, 157--162, 1992.

E. Gassiat, F. Gamboa
Maximum d'entropie et problème des moments : cas multidimensionnel
Prob. and Math. Stat., 12, 1, 67--83, 1991.

E. Gassiat
Problème des moments et concentration de mesure
CRAS. 310,I,41--44, 1990.

 E. Gassiat
Semi-parametric estimation of a stationary non necessary causal AR process with infinite variance
Journal of  Multivariate Analysis, 32, 1,161--170, 1990.

E. Gassiat
Estimation semi-paramétrique d'un modèle autorégressif stationnaire multi-indice non nécessairement causal
Ann. Inst.Henri Poincaré, 26, 1,181-205, 1990.
 
 

PrécédentDÉPARTEMENTDEMATHÉMATIQUESD'ORSAYUniversité Paris-Sud