Distributed Inexact Damped Newton Method: Data Partitioning and Load-Balancing
Machine Learning
2016-03-17 v1 Optimization and Control
Abstract
In this paper we study inexact dumped Newton method implemented in a distributed environment. We start with an original DiSCO algorithm [Communication-Efficient Distributed Optimization of Self-Concordant Empirical Loss, Yuchen Zhang and Lin Xiao, 2015]. We will show that this algorithm may not scale well and propose an algorithmic modifications which will lead to less communications, better load-balancing and more efficient computation. We perform numerical experiments with an regularized empirical loss minimization instance described by a 273GB dataset.
Cite
@article{arxiv.1603.05191,
title = {Distributed Inexact Damped Newton Method: Data Partitioning and Load-Balancing},
author = {Chenxin Ma and Martin Takáč},
journal= {arXiv preprint arXiv:1603.05191},
year = {2016}
}