English

Distributed Multitask Learning

Machine Learning 2015-10-05 v1 Machine Learning

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-22T11:11:30.609Z