709 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université Toulouse III - Paul SabatierFR432 papers
- Université Toulouse - Jean JaurèsFR332 papers
- Université Toulouse-I-CapitoleFR331 papers
- Institut Polytechnique de BordeauxFR326 papers
- Centre National de la Recherche ScientifiqueFR253 papers
- Université de ToulouseFR159 papers
- Institut National Polytechnique de ToulouseFR101 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR92 papers
- École Nationale Supérieure d'Électrotechnique, d'Électronique, d'Informatique, d'Hydraulique et des TélécommunicationsFR52 papers
- Institut national de recherche en sciences et technologies du numériqueFR26 papers
- Institut Universitaire de FranceFR19 papers
- Sorbonne UniversitéFR19 papers
27 papers · 1 filter
On the Wasserstein Geodesic Principal Component Analysis of probability measures
Nina Vesseron, Elsa Cazelles, Alice Le Brigant +1
This paper focuses on Geodesic Principal Component Analysis (GPCA) on a collection of probability distributions using the Otto-Wasserstein geometry. The goal is to identify geodesi…
Scalable Learning from Probability Measures with Mean Measure Quantization
Erell Gachon, Elsa Cazelles, Jérémie Bigot
We consider statistical learning problems in which data are observed as a set of probability measures. Optimal transport (OT) is a popular tool to compare and manipulate such objec…
Analyzing limits for in-context learning
Omar Naim, Jerome Bolte, Nicholas Asher
Our paper challenges claims from prior research that transformer-based models, when learning in context, implicitly implement standard learning algorithms. We present empirical evi…
A distance for mixed-variable and hierarchical domains with meta variables
Edward Hallé-Hannan, Charles Audet, Youssef Diouane +2
Heterogeneous datasets emerge in various machine learning and optimization applications that feature different input sources, types or formats. Most models or methods do not native…
Combining Statistical Depth and Fermat Distance for Uncertainty Quantification
Hai-Vy Nguyen, Fabrice Gamboa, Reda Chhaibi +3
We measure the Out-of-domain uncertainty in the prediction of Neural Networks using a statistical notion called ``Lens Depth'' (LD) combined with Fermat Distance, which is able to…
Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model
Hugo Lebeau, Mohamed El Amine Seddik, José Henrique de Morais Goulart
We study the estimation of a planted signal hidden in a recently introduced nested matrix-tensor model, which is an extension of the classical spiked rank-one tensor model, motivat…
HLoOP -- Hyperbolic 2-space Local Outlier Probabilities
Clémence Allietta, Jean-Philippe Condomines, Jean-Yves Tourneret +1
Hyperbolic geometry has recently garnered considerable attention in machine learning due to its capacity to embed hierarchical graph structures with low distortions for further dow…
Hotelling Deflation on Large Symmetric Spiked Tensors
Mohamed El Amine Seddik, José Henrique de Morais Goulart, Maxime Guillaud
This paper studies the deflation algorithm when applied to estimate a low-rank symmetric spike contained in a large tensor corrupted by additive Gaussian noise. Specifically, we pr…
Gaussian Processes on Distributions based on Regularized Optimal Transport
François Bachoc, Louis Béthune, Alberto Gonzalez-Sanz +1
We present a novel kernel over the space of probability measures based on the dual formulation of optimal regularized transport. We propose an Hilbertian embedding of the space of…
GAN Estimation of Lipschitz Optimal Transport Maps
Alberto González-Sanz, Lucas de Lara, Louis Béthune +1
This paper introduces the first statistically consistent estimator of the optimal transport map between two probability distributions, based on neural networks. Building on theoret…
A Robust and Flexible EM Algorithm for Mixtures of Elliptical Distributions with Missing Data
Florian Mouret, Alexandre Hippert-Ferrer, Frédéric Pascal +1
This paper tackles the problem of missing data imputation for noisy and non-Gaussian data. A classical imputation method, the Expectation Maximization (EM) algorithm for Gaussian m…
Reconstruction of Sentinel-2 Time Series Using Robust Gaussian Mixture Models -- Application to the Detection of Anomalous Crop Development in wheat and rapeseed crops
Florian Mouret, Mohanad Albughdadi, Sylvie Duthoit +3
Missing data is a recurrent problem in remote sensing, mainly due to cloud coverage for multispectral images and acquisition problems. This can be a critical issue for crop monitor…
A Random Matrix Perspective on Random Tensors
José Henrique de Morais Goulart, Romain Couillet, Pierre Comon
Tensor models play an increasingly prominent role in many fields, notably in machine learning. In several applications, such as community detection, topic modeling and Gaussian mix…
A novel notion of barycenter for probability distributions based on optimal weak mass transport
Elsa Cazelles, Felipe Tobar, Joaquín Fontbona
We introduce weak barycenters of a family of probability distributions, based on the recently developed notion of optimal weak transport of mass by Gozlanet al. (2017) and Backhoff…
Particle gradient descent model for point process generation
Antoine Brochard, Bartłomiej Błaszczyszyn, Stéphane Mallat +1
This paper presents a statistical model for stationary ergodic point processes, estimated from a single realization observed in a square window. With existing approaches in stochas…
A Comparative Study of Gamma Markov Chains for Temporal Non-Negative Matrix Factorization
Louis Filstroff, Olivier Gouvert, Cédric Févotte +1
Non-negative matrix factorization (NMF) has become a well-established class of methods for the analysis of non-negative data. In particular, a lot of effort has been devoted to pro…
Learning Disentangled Representations via Mutual Information Estimation
Eduardo Hugo Sanchez, Mathieu Serrurier, Mathias Ortner
In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representatio…
A Quasi-Newton algorithm on the orthogonal manifold for NMF with transform learning
Pierre Ablin, Dylan Fagot, Herwig Wendt +2
Nonnegative matrix factorization (NMF) is a popular method for audio spectral unmixing. While NMF is traditionally applied to off-the-shelf time-frequency representations based on…
Data analysis from empirical moments and the Christoffel function
Edouard Pauwels, Mihai Putinar, Jean-Bernard Lasserre
Spectral features of the empirical moment matrix constitute a resourceful tool for unveiling properties of a cloud of points, among which, density, support and latent structures. I…
Explaining Machine Learning Models using Entropic Variable Projection
François Bachoc, Fabrice Gamboa, Max Halford +2
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,…
Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization
Louis Filstroff, Alberto Lumbreras, Cédric Févotte
We present novel understandings of the Gamma-Poisson (GaP) model, a probabilistic matrix factorization model for count data. We show that GaP can be rewritten free of the score/act…
Bayesian nonparametric Principal Component Analysis
Clément Elvira, Pierre Chainais, Nicolas Dobigeon
Principal component analysis (PCA) is very popular to perform dimension reduction. The selection of the number of significant components is essential but often based on some practi…
An unsupervised bayesian approach for the joint reconstruction and classification of cutaneous reflectance confocal microscopy images
Abdelghafour Halimi, Hadj Batatia, Jimmy Le Digabel +2
This paper studies a new Bayesian algorithm for the joint reconstruction and classification of reflectance confocal microscopy (RCM) images, with application to the identification…
Optimal spectral transportation with application to music transcription
Rémi Flamary, Cédric Févotte, Nicolas Courty +1
Many spectral unmixing methods rely on the non-negative decomposition of spectral data onto a dictionary of spectral templates. In particular, state-of-the-art music transcription…