We consider the problem of distributed multi-task learning, where each machine learns a separate, but related, task. Specifically, each machine learns a linear predictor in high-dimensional space,where all tasks share the same small support. We present a communication-efficient estimator based on the debiased lasso and show that it is comparable with the optimal centralized method.
@article{arxiv.1510.00633,
title = {Distributed Multitask Learning},
author = {Jialei Wang and Mladen Kolar and Nathan Srebro},
journal= {arXiv preprint arXiv:1510.00633},
year = {2015}
}