Distributed Multitask 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.

References in corpus (9)

• Simultaneous analysis of Lasso and Dantzig selector
• Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
• The composite absolute penalties family for grouped and hierarchical variable selection
• A note on the group lasso and a sparse group lasso
• Communication Efficient Distributed Optimization using an Approximate Newton-type Method
• Support union recovery in high-dimensional multivariate regression
• Communication-Efficient Distributed Dual Coordinate Ascent
• Communication-efficient sparse regression: a one-shot approach
• Client-server multi-task learning from distributed datasets

Cited by in corpus (4)

• Efficient Distributed Learning with Sparsity
• Distributed Stochastic Multi-Task Learning with Graph Regularization
• Distributed Multi-Task Learning with Shared Representation
• Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs