Marion Naveau

2024-2026: Postdoctoral researcher at Institut Agro Rennes-Angers. Causality models and Omics data integration to identify the determinants of microbiota recruitment by plant.

2021-2024: PhD at INRAE, Université Paris-Saclay. High-dimensional variable selection procedures in nonlinear mixed effects models. Application in plant breeding.

2020-2021: Master's degree in mathematics applied to life sciences at Université Paris-Saclay.

2020: French agrégation of mathematics.

2018-2019: Master's degree 1 in fundamental mathematics at Université Paris-Saclay.

2017-2018: Bachelor's degree in fundamental mathematics at Université Paris-Saclay.

Title: Causality models and Omics data integration to identify the determinants of microbiota recruitment by plant.

Supervisors: Mathieu Emily (UMR CNRS IRMAR) and Anouk Zancarini (UMR INRAE IGEPP).

Date: 01/12/2024 - 30/11/2026

Funding: PEPR Agro-écologie et Numérique (website)

Title: High-dimensional variable selection procedures in nonlinear mixed effects models. Application in plant breeding.

Supervisors: Maud Delattre (INRAE, MaIAGE) and Laure Sansonnet (INRAE, AgroParisTech, MIA Paris-Saclay).

Start of the PhD: 1 September 2021.

Thesis defense: 27 September 2024

Funding: ANR project Stat4Plant ANR-20-CE45-0012 (website)

High-dimensional data

Variable selection

Non-linear mixed effects models

Bayesian variable selection

Spike-and-slab priors

Selection consistency

Posterior contraction rates

EM algorithm and its extensions

M. Naveau, G. Kon Kam King, R. Rincent, L. Sansonnet, M. Delattre. Bayesian high-dimensional covariate selection in non-linear mixed-effects models using the SAEM algorithm. Statistics and Computing, 2023, 34 (1), pp.53. ⟨10.1007/s11222-023-10367-4⟩. arXiv:2206.01012 link
Erratum B_{nu_0}=|\hat S_{nu_0}| in equation (15)!
Erratum in equation (16), the factorial term in front of the expression in brackets should be:
D phi_i1/(V phi_i1-phi_i2)

M.Naveau, M. Delattre, L. Sansonnet. Posterior contraction rates in a sparse non-linear mixed-effects model, preprint hal-04561040, arXiv:2405.01206 link

Séminaire de Statistique du MAP5, Université Paris-Cité, High-dimensional variable selection in non-linear mixed-effects models : method, application and theoretical guarantees - Paris (France), April 2025

Groupe de travail de Statistique du LMRS, Université de Rouen Normandie, High-dimensional variable selection in non-linear mixed-effects models : method, application and theoretical guarantees - Rouen (France), March 2025

Séminaire de probabilités et statistiques de l'Université d'Angers, High-dimensional variable selection in non-linear mixed-effects models : method, application and theoretical guarantees - Angers (France), March 2025

Séminaire du Laboratoire de Mathématiques Appliquées de Compiègne, High-dimensional variable selection in non-linear mixed-effects models : method, application and theoretical guarantees - Compiègne (France), March 2025

Rencontres Statistiques du CEREMADE, Université Paris-Dauphine, High-dimensional variable selection in non-linear mixed-effects models : method, application and theoretical guarantees - Paris (France), March 2025

Séminaire de Statistiques des doctorants Rennais, High-dimensional variable selection in non-linear mixed-effects models : method, application and theoretical guarantees - Rennes (France), February 2025

Young Statisticians and Probabilists, High-dimensional variable selection in non-linear mixed-effects models - Paris (France), February 2025

Séminaire du Laboratoire de Mathématiques de Versailles, High-dimensional variable selection in non-linear mixed-effects models - Versailles (France), January 2025

Journées scientifiques du PEPR Agroécologie et Numérique, Projet CausMique : Modèles de causalité et intégration de données Omiques pour identifier les déterminants du recrutement du microbiote par la plante - Dijon (France), January 2025

Statistiques aux sommets de Rochebrune, Posterior contraction rates in a sparse non-linear mixed-effects model - Megève (France), March 2024

Colloque Jeunes Probabilistes et Statisticiens, Selection consistency in non-linear mixed-effects models under spike-and-slab prior - Île d'Oléron (France), October 2023

European Meeting of Statisticians, High-dimensional variable selection in non-linear mixed-effects models using a stochastic EM spike-and-slab - Warsaw (Poland), July 2023

Séminaire d'unité de MIA Paris-Saclay, High-dimensional variable selection in non-linear mixed-effects models using a stochastic EM spike-and-slab - Palaiseau (France), June 2023

Séminaire des doctorants de MIA Paris-Saclay, Bayesian high-dimensional variable selection in non-linear mixed-effects models using the SAEM algorithm - Palaiseau (France), December 2022

Séminaire INSERM, labo IAME, équipe BIPID, Bayesian high-dimensional variable selection in non-linear mixed-effects models using the SAEM algorithm - Paris (France), November 2022

ISBA World Meeting (Poster), High-dimensional variable selection in non-linear mixed-effects models using a stochastic EM spike-and-slab - Montréal (Canada), June 2022

53ème Journées de Statistique de la SFdS, Bayesian high-dimensional variable selection in non-linear mixed-effects models using the SAEM algorithm - Lyon (France), June 2022

Journée AppliBUGS, Bayesian high-dimensional variable selection in non-linear mixed-effects models using the SAEM algorithm - Lyon (France), June 2022

9ème Rencontre des Jeunes Statisticiens, High-dimensional variable selection in nonlinear mixed effects models - Porquerolles (France), April 2022

For first-year students: discrete mathematics (logic, set vocabulary, arithmetic, functions/applications), fundamental concepts (matrix calculus, linear systems, polynomials)

For second-year students: mathematics for data security (linear algebra and error-correcting codes), modeling (polynomials, complex numbers, linear algebra and diagonalisation), probabilities (discrete and continuous random variables, sums and sequences of random variables, limit theorems and approximations, probabilistic graphs and Markov chains, random generators)