Jean-Michel Loubes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jean-Michel Loubes has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Elie Maza
LRSV, Université de Toulouse, AgroToulouse, INP, BP 32607, 31326 Castanet-Tolosan, France
4 shared publications Chloé Dimeglio
Institut de Mathématiques de Toulouse Université Toulouse III Paul Sabatier Toulouse France
2 shared publications- Fabrice Gamboa
Institut de Mathématiques de Toulouse
2 shared publications - François Bachoc
Institut de Mathématiques de Toulouse Institut universitaire de France (IUF) School of Economics ANITI School of Economics Toulouse Toulouse Université de Toulouse ANITI & Regalia INRIA
2 shared publications - Laurent Risser
Institut de Mathématiques de Toulouse (IMT), CNRS UMR 5219, Université de Toulouse, Toulouse, France
2 shared publications - Santiago Gallón
Universidad de Antioquía
2 shared publications
Latest Publications
- Open Access
Explaining Machine Learning Models using Entropic Variable Projection
In this paper, we present a new explainability formalism designed to shed light on how each input variable of a test set impacts the predictions of machine learning models. Hence, we propose a group explainability formalism for trained machine learning decision rules, based on their response to the variability of the input variables distribution. In order to emphasize the impact of each input variable, this formalism uses an information theory framework that quantifies the influence of all input-output observations based on entropic projections. This is thus the first unified and model agnostic formalism enabling data scientists to interpret the dependence between the input variables, their impact on the prediction errors, and their influence on the output predictions. Convergence rates of the entropic projections are provided in the large sample case. Most importantly, we prove that computing an explanation in our framework has a low algorithmic complexity, making it scalable to real-life large datasets. We illustrate our strategy by explaining complex decision rules learned by using XGBoost, Random Forest or Deep Neural Network classifiers on various datasets such as Adult Income, MNIST, CelebA, Boston Housing, Iris, as well as synthetic ones. We finally make clear its differences with the explainability strategies LIME and SHAP, that are based on single observations. Results can be reproduced by using the freely distributed Python toolbox https://gems-ai.aniti.fr/.
Open AccessExplaining Machine Learning Models using Entropic Variable Projection
In this paper, we present a new explainability formalism designed to shed light on how each input variable of a test set impacts the predictions of machine learning models. Hence, we propose a group explainability formalism for trained machine learning decision rules, based on their response to the variability of the input variables distribution. In order to emphasize the impact of each input variable, this formalism uses an information theory framework that quantifies the influence of all input-output observations based on entropic projections. This is thus the first unified and model agnostic formalism enabling data scientists to interpret the dependence between the input variables, their impact on the prediction errors, and their influence on the output predictions. Convergence rates of the entropic projections are provided in the large sample case. Most importantly, we prove that computing an explanation in our framework has a low algorithmic complexity, making it scalable to real-life large datasets. We illustrate our strategy by explaining complex decision rules learned by using XGBoost, Random Forest or Deep Neural Network classifiers on various datasets such as Adult Income, MNIST, CelebA, Boston Housing, Iris, as well as synthetic ones. We finally make clear its differences with the explainability strategies LIME and SHAP, that are based on single observations. Results can be reproduced by using the freely distributed Python toolbox https://gems-ai.aniti.fr/.
- Open Access
Gaussian Processes indexed on the symmetric group: prediction and learning
In the framework of the supervised learning of a real function defined on a space X , the so called Kriging method stands on a real Gaussian field defined on X. The Euclidean case is well known and has been widely studied. In this paper, we explore the less classical case where X is the non commutative finite group of permutations. In this setting, we propose and study an harmonic analysis of the covariance operators that enables to consider Gaussian processes models and forecasting issues. Our theory is motivated by statistical ranking problems.
Open AccessGaussian Processes indexed on the symmetric group: prediction and learning
In the framework of the supervised learning of a real function defined on a space X , the so called Kriging method stands on a real Gaussian field defined on X. The Euclidean case is well known and has been widely studied. In this paper, we explore the less classical case where X is the non commutative finite group of permutations. In this setting, we propose and study an harmonic analysis of the covariance operators that enables to consider Gaussian processes models and forecasting issues. Our theory is motivated by statistical ranking problems.
- Open Access
Distribution regression model with a Reproducing Kernel Hilbert Space approach
In this paper, we introduce a new distribution regression model for probability distributions. This model is based on a Reproducing Kernel Hilbert Space (RKHS) regression framework, where universal kernels are built using Wasserstein distances for distributions belonging to W 2 ($\Omega$) and $\Omega$ is a compact subspace of R. We prove the universal kernel property of such kernels and use this setting to perform regressions on functions. Different regression models are first compared with the proposed one on simulated functional data. We then apply our regression model to transient evoked otoascoutic emission (TEOAE) distribution responses and real predictors of the age.Open AccessDistribution regression model with a Reproducing Kernel Hilbert Space approach
In this paper, we introduce a new distribution regression model for probability distributions. This model is based on a Reproducing Kernel Hilbert Space (RKHS) regression framework, where universal kernels are built using Wasserstein distances for distributions belonging to W 2 ($\Omega$) and $\Omega$ is a compact subspace of R. We prove the universal kernel property of such kernels and use this setting to perform regressions on functions. Different regression models are first compared with the proposed one on simulated functional data. We then apply our regression model to transient evoked otoascoutic emission (TEOAE) distribution responses and real predictors of the age. - Open Access
A robust algorithm for template curve estimation based on manifold embedding
This paper considers the problem of finding a meaningful template function that represents the common pattern of a sample of curves. To address this issue, a novel algorithm based on a robust version of the isometric featuring mapping (Isomap) algorithm is developed. Assuming that the functional data lie on an intrinsically low-dimensional smooth manifold with unknown underlying structure, we propose an approximation of the geodesic distance. This approximation is used to compute the corresponding empirical Fr\'echet median function, which provides an intrinsic estimator of the template function. Unlike the Isomap method, the algorithm has the advantage of being parameter free and easier to use. Comparisons with other methods, with both simulated and real datasets, show that the algorithm works well and outperforms these methods.
Open AccessA robust algorithm for template curve estimation based on manifold embedding
This paper considers the problem of finding a meaningful template function that represents the common pattern of a sample of curves. To address this issue, a novel algorithm based on a robust version of the isometric featuring mapping (Isomap) algorithm is developed. Assuming that the functional data lie on an intrinsically low-dimensional smooth manifold with unknown underlying structure, we propose an approximation of the geodesic distance. This approximation is used to compute the corresponding empirical Fr\'echet median function, which provides an intrinsic estimator of the template function. Unlike the Isomap method, the algorithm has the advantage of being parameter free and easier to use. Comparisons with other methods, with both simulated and real datasets, show that the algorithm works well and outperforms these methods.
- Open Access
Functional calibration estimation by the maximum entropy on the mean principle
We extend the problem of obtaining an estimator for the finite population mean parameter incorporating complete auxiliary information through calibration estimation in survey sampling but considering a functional data framework. The functional calibration sampling weights of the estimator are obtained by matching the calibration estimation problem with the maximum entropy on the mean principle. In particular, the calibration estimation is viewed as an infinite dimensional linear inverse problem following the structure of the maximum entropy on the mean approach. We give a precise theoretical setting and estimate the functional calibration weights assuming, as prior measures, the centered Gaussian and compound Poisson random measures. Additionally, through a simple simulation study, we show that our functional calibration estimator improves its accuracy compared with the Horvitz-Thompson estimator.
Open AccessFunctional calibration estimation by the maximum entropy on the mean principle
We extend the problem of obtaining an estimator for the finite population mean parameter incorporating complete auxiliary information through calibration estimation in survey sampling but considering a functional data framework. The functional calibration sampling weights of the estimator are obtained by matching the calibration estimation problem with the maximum entropy on the mean principle. In particular, the calibration estimation is viewed as an infinite dimensional linear inverse problem following the structure of the maximum entropy on the mean approach. We give a precise theoretical setting and estimate the functional calibration weights assuming, as prior measures, the centered Gaussian and compound Poisson random measures. Additionally, through a simple simulation study, we show that our functional calibration estimator improves its accuracy compared with the Horvitz-Thompson estimator.
- Open Access
Manifold embedding for curve registration
We focus on the problem of finding a good representative of a sample of random curves warped from a common pattern f. We first prove that such a problem can be moved onto a manifold framework. Then, we propose an estimation of the common pattern f based on an approximated geodesic distance on a suitable manifold. We then compare the proposed method to more classical methods.
Open AccessManifold embedding for curve registration
We focus on the problem of finding a good representative of a sample of random curves warped from a common pattern f. We first prove that such a problem can be moved onto a manifold framework. Then, we propose an estimation of the common pattern f based on an approximated geodesic distance on a suitable manifold. We then compare the proposed method to more classical methods.
- Open Access
- 1 January 2011
- Published by EDP Sciences in ESAIM: Probability and Statistics
- Vol. 15, 69-82
Local Asymptotic Normality Property for Lacunar Wavelet Series multifractal model
PS : ESAIM: Probability and Statistics, publishes original research and survey papers in the area of Probability and Statistics
- 1 January 2011
- Published by EDP Sciences in ESAIM: Probability and Statistics
- Vol. 15, 69-82
Open AccessLocal Asymptotic Normality Property for Lacunar Wavelet Series multifractal model
PS : ESAIM: Probability and Statistics, publishes original research and survey papers in the area of Probability and Statistics
- 18 November 2010
- Published by Springer Nature in Probability Theory and Related Fields
- Vol. 152 (3-4) , 425-473
Semiparametric estimation of shifts on compact Lie groups for image registration
- 18 November 2010
- Published by Springer Nature in Probability Theory and Related Fields
- Vol. 152 (3-4) , 425-473
Semiparametric estimation of shifts on compact Lie groups for image registration
- 8 October 2009
- Published by Springer Nature in Statistics and Computing
- Vol. 21 (1) , 121-136
Non parametric estimation of the structural expectation of a stochastic increasing function
- 8 October 2009
- Published by Springer Nature in Statistics and Computing
- Vol. 21 (1) , 121-136
Non parametric estimation of the structural expectation of a stochastic increasing function
- 31 March 2009
- Published by Elsevier in Seminars in Orthodontics
- Vol. 15 (1) , 42-47
3D Tooth Modeling for Orthodontic Assessment
- 31 March 2009
- Published by Elsevier in Seminars in Orthodontics
- Vol. 15 (1) , 42-47
3D Tooth Modeling for Orthodontic Assessment