138 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Laboratoire de Mathématiques d'OrsayFR15 papers
- Institut de Mécanique Céleste et de Calcul des ÉphéméridesFR5 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- Centre de Recherche en Économie et StatistiqueFR3 papers
- Université Paris-SaclayFR3 papers
- École PolytechniqueFR2 papers
- EDF Energy (United Kingdom)GB2 papers
- MODAL: MOdel for Data Analysis and LearningFR2 papers
- AgroParisTechFR1 paper
- BNP Paribas (France)FR1 paper
- Care Institute of Medical SciencesIN1 paper
- CEA Paris-Saclay - Etablissement de SaclayFR1 paper
20 papers
GraphToolbox: A Configurable Framework for Controlled Benchmarking of Graph Neural Network Forecasting
Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude +1
Electricity forecasting often involves spatially related signals observed over regions, substations, and feeders, and Graph Neural Networks (GNNs) represent these relations through…
Extreme classification: beating chance with one training example from each class
Kevin Bleakley, Aaditya Ramdas
We study a minimal classification problem: Given independent labeled observations and from two unknown distributions , and given an independent target …
A survey on multi-player bandits
Etienne Boursier, Vianney Perchet
Due mostly to its application to cognitive radio networks, multiplayer bandits gained a lot of interest in the last decade. A considerable progress has been made on its theoretical…
On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits
Antoine Barrier, Aurélien Garivier, Gilles Stoltz
We lay the foundations of a non-parametric theory of best-arm identification in multi-armed bandits with a fixed budget T. We consider general, possibly non-parametric, models D fo…
Contextual Bandits with Knapsacks for a Conversion Model
Zhen Li, Gilles Stoltz
We consider contextual bandits with knapsacks, with an underlying structure between rewards generated and cost vectors suffered. We do so motivated by sales with commercial discoun…
The price of unfairness in linear bandits with biased feedback
Solenne Gaucher, Alexandra Carpentier, Christophe Giraud
In this paper, we study the problem of fair sequential decision making with biased linear bandit feedback. At each round, a player selects an action described by a covariate and by…
Model-based Clustering with Missing Not At Random Data
Aude Sportisse, Matthieu Marbac, Fabien Laporte +4
Model-based unsupervised learning, as any learning task, stalls as soon as missing data occurs. This is even more true when the missing data are informative, or said missing not at…
Hierarchical transfer learning with applications for electricity load forecasting
Anestis Antoniadis, Solenne Gaucher, Yannig Goude
The recent abundance of data on electricity consumption at different scales opens new challenges and highlights the need for new techniques to leverage information present at finer…
Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit
Karl Hajjar, Lénaïc Chizat, Christophe Giraud
To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, t…
A comprehensive guideline for regularization-path variable selection in high-dimensional Gaussian linear regression
Perrine Lacroix, Mélina Gallopin, Marie-Laure Martin
This paper provides a comprehensive comparison of complete regularization-path-based variable selection procedures in high-dimensional Gaussian linear regression. Our simulation st…
Concentration study of M-estimators using the influence function
Timothée Mathieu
We present a new finite-sample analysis of M-estimators of locations in using the tool of the influence function. In particular, we show that the deviations of an M-…
Diversity-Preserving K-Armed Bandits, Revisited
Hédi Hadiji, Sébastien Gerchinovitz, Jean-Michel Loubes +1
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…
Adaptation to the Range in -Armed Bandits
Hédi Hadiji, Gilles Stoltz
We consider stochastic bandit problems with arms, each associated with a bounded distribution supported on the range . We do not assume that the range is known a…
On the robustness of the minimum interpolator
Geoffrey Chinot, Matthieu Lerasle
We analyse the interpolator with minimal -norm in a general high dimensional linear regression framework where where is a ran…
Aggregation of Multiple Knockoffs
Tuan-Binh Nguyen, Jérôme-Alexis Chevalier, Bertrand Thirion +1
We develop an extension of the Knockoff Inference procedure, introduced by Barber and Candes (2015). This new method, called Aggregation of Multiple Knockoffs (AKO), addresses the…
Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification
Evgenii Chzhen, Christophe Denis, Mohamed Hebiri +2
We study the problem of fair binary classification using the notion of Equal Opportunity. It requires the true positive rate to distribute equally across the sensitive groups. With…
Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems
Atsushi Nitanda, Geoffrey Chinot, Taiji Suzuki
Recently, several studies have proven the global convergence and generalization abilities of the gradient descent method for two-layer ReLU networks. Most studies especially focuse…
Minimal penalties and the slope heuristics: a survey
Sylvain Arlot
Birg{é} and Massart proposed in 2001 the slope heuristics as a way to choose optimally from data an unknown multiplicative constant in front of a penalty. It is built upon the noti…
MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Means
Matthieu Lerasle, Zoltan Szabo, Timothee Mathieu +1
Mean embeddings provide an extremely flexible and powerful tool in machine learning and statistics to represent probability distributions and define a semi-metric (MMD, maximum mea…
A Kernel Multiple Change-point Algorithm via Model Selection
Sylvain Arlot, Alain Celisse, Zaid Harchaoui
We tackle the change-point problem with data belonging to a general set. We build a penalty for choosing the number of change-points in the kernel-based method of Harchaoui and Cap…