Federated learning poses new statistical and systems challenges in training machine learning models over distributed networks of devices. In the paper, it is shown that multi-task learning is naturally suited to handle the statistical challenges of this setting, and propose a novel systems-aware optimization method, MOCHA, that is robust to practical systems issues. The resulting method achieves significant speedups compared to alternatives in the federated setting, as we demonstrate through simulations on real-world federated datasets.

Software Requirement: Matlab

How to Run:

1)Download the repository.

2)Run model_driver to get error of models.

3)Run optimizaton_driver to generate plots for run time of models.