2 papers
stat.ML2022
Robust supervised learning with coordinate gradient descent
Stéphane Gaïffas, Ibrahim Merad
This paper considers the problem of supervised learning with linear methods when both features and labels can be corrupted, either in the form of heavy tailed data and/or corrupted…
cs.LG2020
About contrastive unsupervised representation learning for classification and its convergence
Ibrahim Merad, Yiyang Yu, Emmanuel Bacry +1
Contrastive representation learning has been recently proved to be very efficient for self-supervised training. These methods have been successfully used to train encoders which pe…