English

Distributed Optimization for Client-Server Architecture with Negative Gradient Weights

Distributed, Parallel, and Cluster Computing 2016-12-20 v2 Machine Learning Optimization and Control

Abstract

Availability of both massive datasets and computing resources have made machine learning and predictive analytics extremely pervasive. In this work we present a synchronous algorithm and architecture for distributed optimization motivated by privacy requirements posed by applications in machine learning. We present an algorithm for the recently proposed multi-parameter-server architecture. We consider a group of parameter servers that learn a model based on randomized gradients received from clients. Clients are computational entities with private datasets (inducing a private objective function), that evaluate and upload randomized gradients to the parameter servers. The parameter servers perform model updates based on received gradients and share the model parameters with other servers. We prove that the proposed algorithm can optimize the overall objective function for a very general architecture involving CC clients connected to SS parameter servers in an arbitrary time varying topology and the parameter servers forming a connected network.

Keywords

Cite

@article{arxiv.1608.03866,
  title  = {Distributed Optimization for Client-Server Architecture with Negative Gradient Weights},
  author = {Shripad Gade and Nitin H. Vaidya},
  journal= {arXiv preprint arXiv:1608.03866},
  year   = {2016}
}

Comments

[Submitted 12 Aug., 2016. Revised 18 Dec.,2016.] Added Section 3.1, added additional discussion to Section 5, added references