no code implementations • 23 Feb 2024 • Julien Zhou, Pierre Gaillard, Thibaud Rahier, Houssam Zenati, Julyan Arbel
We address the problem of stochastic combinatorial semi-bandits, where a player can select from P subsets of a set containing d base items.
1 code implementation • 26 Dec 2023 • Artem Betlei, Mariia Vladimirova, Mehdi Sebbar, Nicolas Urien, Thibaud Rahier, Benjamin Heymann
The effectiveness of advertising in e-commerce largely depends on the ability of merchants to bid on and win impressions for their targeted users.
no code implementations • 19 Jun 2022 • Matthieu Martin, Panayotis Mertikopoulos, Thibaud Rahier, Houssam Zenati
In many online decision processes, the optimizing agent is called to choose between large numbers of alternatives with many inherent similarities; in turn, these similarities imply closely correlated losses that may confound standard discrete choice models and bandit algorithms.
2 code implementations • 19 May 2022 • Alexandre Ramé, Matthieu Kirchmeyer, Thibaud Rahier, Alain Rakotomamonjy, Patrick Gallinari, Matthieu Cord
Standard neural networks struggle to generalize under distribution shifts in computer vision.
1 code implementation • 19 Nov 2021 • Eustache Diemert, Artem Betlei, Christophe Renaudin, Massih-Reza Amini, Théophane Gregoir, Thibaud Rahier
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 granular level.
no code implementations • 13 Sep 2021 • Amélie Héliou, Matthieu Martin, Panayotis Mertikopoulos, Thibaud Rahier
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 unknown non-convex loss function and only receives the incurred loss as feedback.
no code implementations • NeurIPS 2020 • Amélie Héliou, Matthieu Martin, Panayotis Mertikopoulos, Thibaud Rahier
We consider the problem of online learning with non-convex losses.
no code implementations • 7 Aug 2020 • Thibaud Rahier, Amélie Héliou, Matthieu Martin, Christophe Renaudin, Eustache Diemert
Individual Treatment Effect (ITE) estimation is an extensively researched problem, with applications in various domains.