English

A Sequential Approximation Framework for Coded Distributed Optimization

Information Theory 2017-10-26 v1 Distributed, Parallel, and Cluster Computing Machine Learning Performance math.IT

Abstract

Building on the previous work of Lee et al. and Ferdinand et al. on coded computation, we propose a sequential approximation framework for solving optimization problems in a distributed manner. In a distributed computation system, latency caused by individual processors ("stragglers") usually causes a significant delay in the overall process. The proposed method is powered by a sequential computation scheme, which is designed specifically for systems with stragglers. This scheme has the desirable property that the user is guaranteed to receive useful (approximate) computation results whenever a processor finishes its subtask, even in the presence of uncertain latency. In this paper, we give a coding theorem for sequentially computing matrix-vector multiplications, and the optimality of this coding scheme is also established. As an application of the results, we demonstrate solving optimization problems using a sequential approximation approach, which accelerates the algorithm in a distributed system with stragglers.

Keywords

Cite

@article{arxiv.1710.09001,
  title  = {A Sequential Approximation Framework for Coded Distributed Optimization},
  author = {Jingge Zhu and Ye Pu and Vipul Gupta and Claire Tomlin and Kannan Ramchandran},
  journal= {arXiv preprint arXiv:1710.09001},
  year   = {2017}
}

Comments

presented in 55th Annual Allerton Conference on Communication, Control, and Computing, Oct. 2017