Is it possible to perform linear regression on datasets whose labels are shuffled with respect
to the inputs? We explore this question by proposing several estimators that recover the …

We consider the problem of inference in a linear regression model in which the relative
ordering of the input features and output labels is not known. Such datasets naturally arise …

We consider the problem of inference in a linear regression model in which the relative
ordering of the input features and output labels is not known. Such datasets naturally arise …

We propose in this work a new unsupervised training procedure that is most effective when it
is applied after supervised training and fine-tuning of deep neural network classifiers. While …

In Machine Learning field, data characteristics usually vary over the space: the overall
distribution might be multi-modal and contain non-linearities. In order to achieve good …

Nous proposons ainsi un modèle simple de grossissement permettant d'ajouter
progressivement des nouveaux paramètres au cours de l'apprentissage afin d'étudier les …

Machine learning is a field of Artificial Intelligence which encompasses algorithms allowing
a computer to perform a task without being manually programmed for. In general, the …