Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares release_u3hyxgym25gdze3yoevrajbbpm

by Junqi Tang, Mohammad Golbabaee, Mike Davies

Released as a article .

2017  

Abstract

We propose a randomized first order optimization algorithm Gradient Projection Iterative Sketch (GPIS) and an accelerated variant for efficiently solving large scale constrained Least Squares (LS). We provide theoretical convergence analysis for both proposed algorithms and demonstrate our methods' computational efficiency compared to classical accelerated gradient method, and the state of the art variance-reduced stochastic gradient methods through numerical experiments in various large synthetic/real data sets.
In text/plain format

Archived Files and Locations

application/pdf  343.9 kB
file_jqbrq43mwzce5mnpknykdushvu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-02-24
Version   v3
Language   en ?
arXiv  1609.09419v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: fd1710a9-f1aa-4a03-8136-c384da0e0b53
API URL: JSON