Home
Resource
From coordinate descent to social sampling
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(411.38 kb)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Ghassemi, Mohsen. From coordinate descent to social sampling. Retrieved from https://doi.org/doi:10.7282/T3M90BTP

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleFrom coordinate descent to social sampling
NameGhassemi, Mohsen (author); Sarwate, Anand (chair); Bajwa, Waheed (internal member); Patel, Vishal (internal member); Rutgers University; Graduate School - New Brunswick
Date Created2016
Other Date2016-05 (degree)
SubjectElectrical and Computer Engineering, Stochastic processes, Big data
Extent1 online resource (vi, 70 p. : ill.)
DescriptionThe unprecedented rate at which data is being created and stored calls for scalable optimization techniques that allow e cient Big Data" analysis. In this work where there is only one computing node, that modi es the coordinate-sampling distribution for stochastic coordinate descent: we call this proportional stochastic coordinate descent (PSCD). This method treats the gradient of the function as a probability distribution to sample the coordinates, and may be useful in so-called lock-free decentralized optimization schemes. Although stochastic coordinate descent methods seem attractive due to their small per-iteration complexity, they show high variance in performance compared to full gradient descent algorithms. In order to address this issue we propose stochastic variance reduced coordinate descent that takes information from the previous gradient estimates into account. Lastly, we consider stochastic message passing algorithms that limit the communication required for decentralized and distributed convex optimization and provide convergence guarantees on the objective value. For general distributed optimization in which agents jointly minimize the sum of local objectives we propose treating the iterates as gradients and propose a stochastic coordinate-wise primal averaging algorithm for optimization.
NoteM.S.
NoteIncludes bibliographical references
Noteby Mohsen Ghassemi
Genretheses, ETD graduate
Persistent URLhttps://doi.org/doi:10.7282/T3M90BTP
Languageeng
CollectionGraduate School - New Brunswick Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024