Federated kernelized multi-task learning

Federated learning poses new statistical and systems challenges in the training of machine learning models over distributed networks of devices. In this ongoing work, we develop a state of the art MTL federated system that bypasses the modelling limitations of previous efforts through the inclusion of non-linear mappings in its formulation. We address the new issues that arise due to this inclusion and that are associated with the particulars of the federated scenario, such as communication and storage costs, introducing this way the first fully practical kernelized federated framework.