no code implementations • 9 Apr 2024 • Mahdi Tavassoli Kejani, Fadi Dornaika, Jean-Michel Loubes
In recent years, Graph Neural Networks (GNNs) have made significant advancements, particularly in tasks such as node classification, link prediction, and graph representation.
no code implementations • 23 Feb 2024 • Renan D. B. Brotto, Jean-Michel Loubes, Laurent Risser, Jean-Pierre Florens, Kenji Nose-Filho, João M. T. Romano
In our work, we then propose a bias mitigation strategy for continuous sensitive variables, based on the notion of endogeneity which comes from the field of econometrics.
no code implementations • 10 Oct 2023 • Marouane Il Idrissi, Nicolas Bousquet, Fabrice Gamboa, Bertrand Iooss, Jean-Michel Loubes
The elements of this decomposition can be expressed using oblique projections and allow for novel interpretability indices for evaluation and variance decomposition purposes.
1 code implementation • 28 Aug 2023 • François Bachoc, Louis Béthune, Alberto González-Sanz, Jean-Michel Loubes
In this paper, we improve the learning theory of kernel distribution regression.
no code implementations • 8 Jun 2023 • Fanny Jourdan, Laurent Risser, Jean-Michel Loubes, Nicholas Asher
This paper presents novel experiments shedding light on the shortcomings of current metrics for assessing biases of gender discrimination made by machine learning algorithms on textual data.
no code implementations • 27 Feb 2023 • Fanny Jourdan, Titon Tshiongo Kaninku, Nicholas Asher, Jean-Michel Loubes, Laurent Risser
To anticipate the certification of recommendation systems using textual data, we then used it on the Bios dataset, for which the learning task consists in predicting the occupation of female and male individuals, based on their LinkedIn biography.
1 code implementation • 14 Feb 2023 • Natasa Krco, Thibault Laugel, Jean-Michel Loubes, Marcin Detyniecki
With comparable performances in fairness and accuracy, are the different bias mitigation approaches impacting a similar number of individuals?
no code implementations • 12 Oct 2022 • François Bachoc, Louis Béthune, Alberto Gonzalez-Sanz, Jean-Michel Loubes
We present a novel kernel over the space of probability measures based on the dual formulation of optimal regularized transport.
no code implementations • 10 Oct 2022 • Laurent Risser, Agustin Picard, Lucas Hervier, Jean-Michel Loubes
Contrarily to societal applications where a set of proxy variables can be provided by the common sense or by regulations to draw the attention on potential risks, industrial and safety-critical applications are most of the times sailing blind.
1 code implementation • 23 Sep 2022 • Marouane Il Idrissi, Nicolas Bousquet, Fabrice Gamboa, Bertrand Iooss, Jean-Michel Loubes
Numerical experiments on real case studies, from the UQ and ML fields, highlight the computational feasibility of such studies and provide local and global insights on the robustness of black-box models to input perturbations.
no code implementations • 23 Apr 2022 • William Todo, Beatrice Laurent, Jean-Michel Loubes, Merwann Selmani
In this work, we explore dimensionality reduction techniques for univariate and multivariate time series data.
no code implementations • 19 Apr 2022 • Eustasio del Barrio, Alberto Gonzalez-Sanz, Jean-Michel Loubes, Jonathan Niles-Weed
We prove a central limit theorem for the entropic transportation cost between subgaussian probability measures, centered at the population cost.
no code implementations • 16 Feb 2022 • Alberto González-Sanz, Lucas de Lara, Louis Béthune, Jean-Michel Loubes
This paper introduces the first statistically consistent estimator of the optimal transport map between two probability distributions, based on neural networks.
no code implementations • 16 Feb 2022 • Samuele Centorrino, Jean-Pierre Florens, Jean-Michel Loubes
A {\it fair} solution is obtained by projecting the unconstrained index into the null space of this operator or by directly finding the closest solution of the functional equation into this null space.
1 code implementation • 30 Aug 2021 • Lucas de Lara, Alberto González-Sanz, Nicholas Asher, Laurent Risser, Jean-Michel Loubes
We address the problem of designing realistic and feasible counterfactuals in the absence of a causal model.
no code implementations • 5 Oct 2020 • Hédi Hadiji, Sébastien Gerchinovitz, Jean-Michel Loubes, Gilles Stoltz
We consider the bandit-based framework for diversity-preserving recommendations introduced by Celis et al. (2019), who approached it in the case of a polytope mainly by a reduction to the setting of linear bandits.
1 code implementation • CVPR 2021 • Mathieu Serrurier, Franck Mamalet, Alberto González-Sanz, Thibaut Boissin, Jean-Michel Loubes, Eustasio del Barrio
This loss function has a direct interpretation in terms of adversarial robustness together with certifiable robustness bound.
no code implementations • 9 Jun 2020 • Eustasio del Barrio, Jean-Michel Loubes
We propose to tackle the problem of understanding the effect of regularization in Sinkhorn algotihms.
no code implementations • 26 May 2020 • Eustasio del Barrio, Paula Gordaliza, Jean-Michel Loubes
A review of the main fairness definitions and fair learning methodologies proposed in the literature over the last years is presented from a mathematical point of view.
no code implementations • 24 May 2020 • Thibaut Le Gouic, Jean-Michel Loubes, Philippe Rigollet
In the context of regression, we consider the fundamental question of making an estimator fair while preserving its prediction accuracy as much as possible.
1 code implementation • 31 Mar 2020 • Philippe Besse, Eustasio del Barrio, Paula Gordaliza, Jean-Michel Loubes, Laurent Risser
Applications based on Machine Learning models have now become an indispensable part of the everyday life and the professional world.
no code implementations • 11 Feb 2020 • Joseph Lam-Weil, Béatrice Laurent, Jean-Michel Loubes
To the best of our knowledge, we provide the first minimax optimal test and associated private transformation under a local differential privacy constraint over Besov balls in the continuous setting, quantifying the price to pay for data privacy.
no code implementations • 15 Aug 2019 • Laurent Risser, Alberto Gonzalez Sanz, Quentin Vincenot, Jean-Michel Loubes
We then introduce in this paper a new method to temper the algorithmic bias in Neural-Network based classifiers.
1 code implementation • 18 Jul 2019 • Eustasio del Barrio, Hristo Inouzhe, Jean-Michel Loubes, Carlos Matrán, Agustín Mayo-Íscar
We also present $optimalFlowClassification$, which uses a database of gated cytometries and optimalFlowTemplates to assign cell types to a new cytometry.
1 code implementation • 10 Apr 2019 • Eustasio del Barrio, Hristo Inouzhe, Jean-Michel Loubes
We consider the problem of diversity enhancing clustering, i. e, developing clustering methods which produce clusters that favour diversity with respect to a set of protected attributes such as race, sex, age, etc.
2 code implementations • 18 Oct 2018 • François Bachoc, Fabrice Gamboa, Max Halford, Jean-Michel Loubes, Laurent Risser
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.
no code implementations • 3 Oct 2018 • Philippe Besse, Celine Castets-Renard, Aurelien Garivier, Jean-Michel Loubes
Combining big data and machine learning algorithms, the power of automatic decision tools induces as much hope as fear.
2 code implementations • 17 Jul 2018 • Philippe Besse, Eustasio del Barrio, Paula Gordaliza, Jean-Michel Loubes
We provide the asymptotic distribution of the major indexes used in the statistical literature to quantify disparate treatment in machine learning.
1 code implementation • 8 Jun 2018 • Eustasio del Barrio, Fabrice Gamboa, Paula Gordaliza, Jean-Michel Loubes
\textit{Fairness} is generally studied in a probabilistic framework where it is assumed that there exists a protected variable, whose use as an input of the algorithm may imply discrimination.
Statistics Theory Statistics Theory 62H30, 68T01
no code implementations • 25 May 2018 • Camille Champion, Anne-Claire Brunet, Jean-Michel Loubes, Laurent Risser
In this paper, we present a new R package COREclust dedicated to the detection of representative variables in high dimensional spaces with a potentially limited number of observations.
no code implementations • 16 Mar 2018 • François Bachoc, Baptiste Broto, Fabrice Gamboa, Jean-Michel Loubes
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.
no code implementations • 13 Dec 2017 • Clémentine Barreyre, Béatrice Laurent, Jean-Michel Loubes, Bertrand Cabon, Loïc Boussouf
We propose a novel procedure for outlier detection in functional data, in a semi-supervised framework.
no code implementations • 2 Oct 2017 • Thomas Epelbaum, Fabrice Gamboa, Jean-Michel Loubes, Jessica Martin
In this paper, we propose deep learning architectures (FNN, CNN and LSTM) to forecast a regression model for time dependent data.
no code implementations • 31 Jan 2017 • François Bachoc, Fabrice Gamboa, Jean-Michel Loubes, Nil Venet
We prove that the Gaussian processes indexed by distributions corresponding to these kernels can be efficiently forecast, opening new perspectives in Gaussian process modeling.
no code implementations • 30 Sep 2016 • Philippe Besse, Brendan Guillouet, Jean-Michel Loubes
Management and analysis of big data are systematically associated with a data distributed architecture in the Hadoop and now Spark frameworks.
no code implementations • 10 May 2016 • Philippe C. Besse, Brendan Guillouet, Jean-Michel Loubes, Francois Royer
We present how this model can be used to predict the final destination of a new trajectory based on their first locations using a two step procedure: We first assign the new trajectory to the clusters it mot likely belongs.
1 code implementation • 20 Aug 2015 • Philippe Besse, Brendan Guillouet, Jean-Michel Loubes, Royer François
Using clustering technics based on the choice of a distance between the observations, we first provide a comprehensive review of the different distances used in the literature to compare trajectories.