1 code implementation • 20 Feb 2024 • Rahul Bordoloi, Clémence Réda, Orell Trautmann, Saptarshi Bej, Olaf Wolkenhauer
However, in the age of large multivariate and incomplete data, statistical dependencies between features must be estimated in a computationally tractable way, while also dealing with missing data.
no code implementations • 16 Oct 2023 • Marc Jourdan, Clémence Réda
Second, when APGAI is combined with a stopping rule, we prove upper bounds on the expected sampling complexity, holding at any confidence level.
1 code implementation • 31 May 2022 • Clémence Réda, Sattar Vakili, Emilie Kaufmann
In this paper, we provide new lower bounds on the sample complexity of pure exploration and on the regret.
1 code implementation • NeurIPS 2021 • Clémence Réda, Andrea Tirinzoni, Rémy Degenne
In this work, we first derive a tractable lower bound on the sample complexity of any $\delta$-correct algorithm for the general Top-m identification problem.
1 code implementation • 18 Mar 2021 • Clémence Réda, Emilie Kaufmann, Andrée Delahaye-Duriez
Motivated by an application to drug repurposing, we propose the first algorithms to tackle the identification of the m $\ge$ 1 arms with largest means in a linear bandit model, in the fixed-confidence setting.