Paper Info
Title
Distributed Inexact Damped Newton Method: Data Partitioning and Load-Balancing.
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.
Year
Venue
Field
2016
national conference on artificial intelligence
Mathematical optimization,Distributed Computing Environment,Computer science,Load balancing (computing),Loss minimization,Artificial intelligence,Data partitioning,Machine learning,Computation,Newton's method
DocType
Volume
Citations 
Journal
abs/1603.05191
1
PageRank 
References 
Authors
0.34
20
2
Name
Order
Citations
PageRank
Chenxin Ma1735.25
Martin Takác275249.49