9 citations
- Centre National de la Recherche ScientifiqueFR3 papers
- Afterschool AllianceUS2 papers
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR2 papers
- École Centrale de LilleFR2 papers
- Institut national de recherche en sciences et technologies du numériqueFR2 papers
- Université de LilleFR2 papers
- Institut de Biologie Intégrative de la CelluleFR1 paper
- National University of SingaporeSG1 paper
- Vrije Universiteit AmsterdamNL1 paper
5 papers
Risk-aware linear bandits with convex loss
Patrick Saux, Odalric-Ambrym Maillard
In decision-making problems such as the multi-armed bandit, an agent learns sequentially by optimizing a certain feedback. While the mean reward criterion has been extensively stud…
Choosing Answers in -Best-Answer Identification for Linear Bandits
Marc Jourdan, Rémy Degenne
In pure-exploration problems, information is gathered sequentially to answer a question on the stochastic environment. While best-arm identification for linear bandits has been ext…
Top Two Algorithms Revisited
Marc Jourdan, Rémy Degenne, Dorian Baudry +2
Top Two algorithms arose as an adaptation of Thompson sampling to best arm identification in multi-armed bandit models (Russo, 2016), for parametric families of arms. They select t…
How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis
Bishwamittra Ghosh, Debabrota Basu, Kuldeep S. Meel
Fairness in machine learning has attained significant focus due to the widespread application in high-stake decision-making tasks. Unregulated machine learning classifiers can exhi…
Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithm
Debabrota Basu, Odalric-Ambrym Maillard, Timothée Mathieu
We study the corrupted bandit problem, i.e. a stochastic multi-armed bandit problem with unknown reward distributions, which are heavy-tailed and corrupted by a history-indepen…