Timezone: »

Adaptive Algorithms for Relaxed Pareto Set Identification
Cyrille KONE · Emilie Kaufmann · Laura Richert

Thu Dec 14 03:00 PM -- 05:00 PM (PST) @ Great Hall & Hall B1+B2 #1806
In this paper we revisit the fixed-confidence identification of the Pareto optimal set in a multi-objective multi-armed bandit model. As the sample complexity to identify the exact Pareto set can be very large, a relaxation allowing to output some additional near-optimal arms has been studied. In this work we also tackle alternative relaxations that allow instead to identify a relevant \emph{subset} of the Pareto set. Notably, we propose a single sampling strategy, called Adaptive Pareto Exploration, that can be used in conjunction with different stopping rules to take into account different relaxations of the Pareto Set Identification problem. We analyze the sample complexity of these different combinations, quantifying in particular the reduction in sample complexity that occurs when one seeks to identify at most $k$ Pareto optimal arms. We showcase the good practical performance of Adaptive Pareto Exploration on a real-world scenario, in which we adaptively explore several vaccination strategies against Covid-19 in order to find the optimal ones when multiple immunogenicity criteria are taken into account.

Author Information

Cyrille KONE (Inria Scool)

I am a PhD candidate at the Inria Lille’s Scool team (ex SequeL), under the supervision of Emilie Kaufmann (CNRS / Inria researcher) and Laura Richert (Inserm/Inria researcher). Before my PhD, I graduated from ENS Rennes and ENS Paris-Saclay.

Emilie Kaufmann (CNRS)
Laura Richert (University of Bordeaux)

More from the Same Authors