Work

Distributed Multitask Learning

Year: 2015
Type: preprint
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.
Language: English
Open Access status: green
OpenAlex ID: W2236749180
Cites: 43
Cited by: 60
Related to: 10