Journées Statistiques du Sud 2024

Session

Exposé court

18 juin 2024, 13:00

Salle Johnson (IMT, Université Paul Sabatier)

Présidents de session

Exposé court: Applications Bio & Santé

• Nicolas Enjalbert Courrech (Institut de Mathématiques de Toulouse)

Exposé court: Machine Learning

• Sophia YAZZOURH (Institut de Mathématiques de Toulouse)

Exposé court: Compressed and distributed least-squares regression: convergence rates with applications to Federated Learning

• Constantin Philippenko (Ecole Polytechnique)

19. HSMM piloté par les observations pour l'estimation de la dynamique des adventices

Hanna Bacave (INRAE, MIAT)

18/06/2024 13:00

Pré-journée pour les étudiant.es

Les adventices sont des plantes qui poussent spontanément dans les parcelles agricoles et qui entrent en compétition avec les cultures. Leur dynamique repose sur la colonisation et la dormance. La banque de graines n'étant jamais observée de manière naturelle, une modélisation de cette dynamique a été proposée dans le cadre des Hidden Markov Models (HMM). Ce modèle, appelé Observation...

11. One-Step estimation procedure in univariate and multivariate GLMs with categorical explanatory variables

Mme Lilit Hovsepyan (Laboratoire Manceau de Mathématiques - Inrae Toulouse)

18/06/2024 13:25

Pré-journée pour les étudiant.es

Generalized linear models are commonly used for modeling relationships in both univariate and multivariate contexts, with parameters traditionally estimated via the maximum likelihood estimator (MLE). MLE, while efficient, often requires a Newton-Raphson type algorithm for computation, making it time-intensive particularly with large datasets or numerous variables. Although faster, alternative...

16. Bayesian Outcome Weighted Learning

Sophia YAZZOURH (Institut de Mathématiques de Toulouse)

18/06/2024 13:50

Pré-journée pour les étudiant.es

L'un des objectifs principaux de la médecine de précision statistique est d'apprendre des règles de traitement individualisées optimales ou "Individualized Treatment Rules" (ITRs). La méthode "Outcome Weighted Learning" (OWL) propose pour la première fois, une approche basée sur la classification, ou l'apprentissage automatique, pour estimer les ITRs. Elle reformule le problème d'apprentissage...

27. A general approximation lower bound in Lp norm, with applications to feed-forward neural networks

Armand Foucault (université de Toulouse, ANITI)

18/06/2024 14:45

Pré-journée pour les étudiant.es

We study the fundamental limits to the expressive power of neural networks. Given two sets F, G of real-valued functions, we first prove a general lower bound on how well functions in F can be approximated in Lp(μ) norm by functions in G, for any p≥1 and any probability measure μ. The lower bound depends on the packing number of F, the range of F, and the fat-shattering dimension of G. We then...

26. Variational autoencoder with weighted samples for high-dimensional non-parametric adaptive importance sampling

Julien Demange-Chryst (ONERA - IMT)

18/06/2024 15:10

Pré-journée pour les étudiant.es

Adaptive importance sampling is a well-known family of algorithms for density approximation, generation and Monte Carlo integration including rare event estimation. The main common denominator of this family of algorithms is to perform density estimation with weighted samples at each iteration. However, the classical existing methods to do so, such as kernel smoothing or approximation by a...

17. Physics-Informed Machine Learning methods applied to inverse problems in river hydraulics

Hugo Boulenc (IMT - INSA Toulouse)

18/06/2024 15:35

Pré-journée pour les étudiant.es

Faced with the socio-economic challenges of flood forecasting, in a context of climate change, multi-scale modeling approaches that take advantage of the maximum amount of information available are needed to enable accurate and rapid flood forecasts.

In this context, the objective of this work is to develop a Physics-Informed Machine Learning method to efficiently perform flood models...

25. Compressed and distributed least-squares regression: convergence rates with applications to Federated Learning

Constantin Philippenko (Ecole Polytechnique)

20/06/2024 09:00

Exposés courts

We investigate the impact of compression on stochastic gradient algorithms for machine learning, a technique widely used in distributed and federated learning.
We underline differences in terms of convergence rates between several unbiased compression operators, that all satisfy the same condition on their variance, thus going beyond the classical worst-case analysis. To do so, we focus on...

18. A Bayesian Framework for Multivariate Differential Analysis accounting for Missing Data

Marie Chion (MRC Biostatistics Unit, University of Cambridge)

Exposés courts

Current statistical methods in differential proteomics analysis generally leave aside several challenges, such as missing values, correlations between peptide intensities and uncertainty quantification. Moreover, they provide point estimates, such as the mean intensity for a given peptide or protein in a given condition. The decision of whether an analyte should be considered as differential...