Appears in collection : 10e Journée Statistique et Informatique pour la Science des Données à Paris-Saclay

In this talk, we present a practical solution to the lack of prediction diversity observed recently for deep learning approaches when used out-of-distribution. Considering that this issue is mainly related to a lack of weight diversity, we introduce the maximum entropy principle for the weight distribution coupled with the standard, task-dependent, in-distribution data fitting term. We prove numerically that the derived algorithm is systematically relevant. We also plan to us this strategy to make out-of-distribution predictions about the future of data (science) scientists.