259 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Centre de Recherche en Économie et StatistiqueFR18 papers
- Centre Inria de SaclayFR16 papers
- Centre National de la Recherche ScientifiqueFR14 papers
- Sorbonne UniversitéFR14 papers
- Laboratoire d'Informatique de GrenobleFR12 papers
- École Normale Supérieure Paris-SaclayFR11 papers
- ENSAE ParisFR11 papers
- École Nationale d'AdministrationSN9 papers
- Laboratoire d'Informatique, du Traitement de l'Information et des SystèmesFR8 papers
- École PolytechniqueFR7 papers
- Institut Systèmes Intelligents et de RobotiqueFR7 papers
- POLARIS: Évaluation et optimisation des performances des grandes infrastructuresFR6 papers
22 papers · 1 filter
A Large Scale Benchmark for Individual Treatment Effect Prediction and Uplift Modeling
Eustache Diemert, Artem Betlei, Christophe Renaudin +3
Individual Treatment Effect (ITE) prediction is an important area of research in machine learning which aims at explaining and estimating the causal impact of an action at the gran…
EdiBERT, a generative model for image editing
Thibaut Issenhuth, Ugo Tanielian, Jérémie Mary +1
Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks. However, a specialized model is often d…
Statistical and Topological Properties of Gaussian Smoothed Sliced Probability Divergences
Alain Rakotomamonjy, Mokhtar Z. Alaya, Maxime Berar +1
Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It has been shown, in appl…
Mapping conditional distributions for domain adaptation under generalized target shift
Matthieu Kirchmeyer, Alain Rakotomamonjy, Emmanuel de Bezenac +1
We consider the problem of unsupervised domain adaptation (UDA) between a source and a target domain under conditional and label shift a.k.a Generalized Target Shift (GeTarS). Unli…
Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction
Bruno Taillé, Vincent Guigue, Geoffrey Scoutheeten +1
State-of-the-art NLP models can adopt shallow heuristics that limit their generalization capability (McCoy et al., 2019). Such heuristics include lexical overlap with the training…
Zeroth-order non-convex learning via hierarchical dual averaging
Amélie Héliou, Matthieu Martin, Panayotis Mertikopoulos +1
We propose a hierarchical version of dual averaging for zeroth-order online non-convex optimization - i.e., learning processes where, at each stage, the optimizer is facing an unkn…
A heuristic for estimating Nash equilibria in first-price auctions with correlated values
Benjamin Heymann, Panayotis Mertikopoulos
Our paper concerns the computation of Nash equilibria of first-price auctions with correlated values. While there exist several equilibrium computation methods for auctions with in…
Causal Inference Theory with Information Dependency Models
Benjamin Heymann, Michel de Lara, Jean-Philippe Chancelier
Inferring the potential consequences of an unobserved event is a fundamental scientific question. To this end, Pearl's celebrated do-calculus provides a set of inference rules to d…
Topological Conditional Separation
Michel de Lara, Jean-Philippe Chancelier, Benjamin Heymann
Pearl's d-separation is a foundational notion to study conditional independence between random variables. We define the topological conditional separation and we show that it is eq…
Pure Exploration and Regret Minimization in Matching Bandits
Flore Sentenac, Jialin Yi, Clément Calauzènes +2
Finding an optimal matching in a weighted graph is a standard combinatorial problem. We consider its semi-bandit version where either a pair or a full matching is sampled sequentia…
Combining Reward and Rank Signals for Slate Recommendation
Imad Aouali, Sergey Ivanov, Mike Gartrell +4
We consider the problem of slate recommendation, where the recommender system presents a user with a collection or slate composed of K recommended items at once. If the user finds…
Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements
Kimon Antonakopoulos, Panayotis Mertikopoulos
We propose a new family of adaptive first-order methods for a class of convex minimization problems that may fail to be Lipschitz continuous or smooth in the standard sense. Specif…
The Last-Iterate Convergence Rate of Optimistic Mirror Descent in Stochastic Variational Inequalities
Waïss Azizian, Franck Iutzeler, Jérôme Malick +1
In this paper, we analyze the local convergence rate of optimistic mirror descent methods in stochastic variational inequalities, a class of optimization problems with important ap…
Asymptotic Degradation of Linear Regression Estimates With Strategic Data Sources
Benjamin Roussillon, Nicolas Gast, Patrick Loiseau +1
We consider the problem of linear regression from strategic data sources with a public good component, i.e., when data is provided by strategic agents who seek to minimize an indiv…
LEADS: Learning Dynamical Systems that Generalize Across Environments
Yuan Yin, Ibrahim Ayed, Emmanuel de Bézenac +2
When modeling dynamical systems from real-world data samples, the distribution of data often changes according to the environment in which they are captured, and the dynamics of th…
Decentralized Learning in Online Queuing Systems
Flore Sentenac, Etienne Boursier, Vianney Perchet
Motivated by packet routing in computer networks, online queuing systems are composed of queues receiving packets at different rates. Repeatedly, they send packets to servers, each…
Heterogeneous Wasserstein Discrepancy for Incomparable Distributions
Mokhtar Z. Alaya, Gilles Gasso, Maxime Berar +1
Optimal Transport (OT) metrics allow for defining discrepancies between two probability measures. Wasserstein distance is for longer the celebrated OT-distance frequently-used in t…
Decomposition-Coordination Method for Finite Horizon Bandit Problems
Michel de Lara, Benjamin Heymann, Jean-Philippe Chancelier
Optimally solving a multi-armed bandit problem suffers the curse of dimensionality. Indeed, resorting to dynamic programming leads to an exponential growth of computing time, as th…
QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning
Maxime Vono, Vincent Plassier, Alain Durmus +2
The objective of Federated Learning (FL) is to perform statistical inference for data which are decentralised and stored locally on networked clients. FL raises many constraints wh…
Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium
Yu-Guan Hsieh, Kimon Antonakopoulos, Panayotis Mertikopoulos
In game-theoretic learning, several agents are simultaneously following their individual interests, so the environment is non-stationary from each player's perspective. In this con…
Regret Bounds for Generalized Linear Bandits under Parameter Drift
Louis Faury, Yoan Russac, Marc Abeille +1
Generalized Linear Bandits (GLBs) are powerful extensions to the Linear Bandit (LB) setting, broadening the benefits of reward parametrization beyond linearity. In this paper we st…
Boost then Convolve: Gradient Boosting Meets Graph Neural Networks
Sergei Ivanov, Liudmila Prokhorenkova
Graph neural networks (GNNs) are powerful models that have been successful in various graph representation learning tasks. Whereas gradient boosted decision trees (GBDT) often outp…