Distributed Multi-Task Learning with Shared Representation

03/07/2016

∙

by   Jialei Wang, et al.

∙

0

∙

share

We study the problem of distributed multi-task learning with shared representation, where each machine aims to learn a separate, but related, task in an unknown shared low-dimensional subspaces, i.e. when the predictor matrix has low rank. We consider a setting where each task is handled by a different machine, with samples for the task available locally on the machine, and study communication-efficient methods for exploiting the shared structure.