@inproceedings{e33f3c12531449b595552269a469174b,
title = "Data-dependent bounds on network gradient descent",
abstract = "We study a consensus-based distributed stochastic gradient method for distributed optimization in a setting common for machine learning applications. Nodes in the network hold disjoint data and seek to optimize a common objective which decomposes into a sum of convex functions of individual data points. We show that the rate of convergence for this method involves the spectral properties of two matrices: the standard spectral gap of a weight matrix from the network topology and a new term depending on the spectral norm of the sample covariance matrix of the data. This result shows the benefit of datasets with small spectral norm. Extensions of the method can identify the impact of limited communication, increasing the number of nodes, and scaling with data set size.",
author = "Avleen Bijral and Sarwate, {Anand D.} and Nathan Srebro",
note = "Funding Information: This work was supported by the National Science Foundation under award CCF-1440033 Publisher Copyright: {\textcopyright} 2016 IEEE.; 54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016 ; Conference date: 27-09-2016 Through 30-09-2016",
year = "2017",
month = feb,
day = "10",
doi = "10.1109/ALLERTON.2016.7852325",
language = "English (US)",
series = "54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "869--874",
booktitle = "54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016",
address = "United States",
}