资源分类
》 资源 》论文》Efficient Distributed Learning with Sparsity

Efficient Distributed Learning with Sparsity

2020-03-09 | |  54 |   53 |   0

Abstract

We propose a novel, efficient approach for distributed sparse learning with observations randomly partitioned across machines. In each round of the proposed method, worker machines compute the gradient of the loss on local data and the master machine solves a shifted 图片.png regularized loss minimization problem. After a number of communication rounds that scales only logarithmically with the number of machines, and independent of other parameters of the problem, the proposed approach provably matches the estimation error bound of centralized methods.

上一篇：Decoupled Neural Interfaces using Synthetic Gradients

下一篇：Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...