Finito: A faster, permutable incremental gradient method for big data problems
Defazio, Aaron; Caetano, Tiberio; Domke, Justin
Description
Recent advances in optimization theory have shown that smooth strongly convex finite sums can be minimized faster than by treating them as a black box "batch" problem. In this work we introduce a new method in this class with a theoretical convergence rate four times faster than ex-isting methods, for sums with sufficiently many terms. This method is also amendable to a sampling without replacement scheme that in practice gives further speed-ups. We give empirical results showing state of the...[Show more]
dc.contributor.author | Defazio, Aaron | |
---|---|---|
dc.contributor.author | Caetano, Tiberio | |
dc.contributor.author | Domke, Justin | |
dc.coverage.spatial | Beijing, China | |
dc.date.accessioned | 2015-12-10T22:41:28Z | |
dc.date.created | June 21-26 2014 | |
dc.identifier.isbn | 9781634393973 | |
dc.identifier.uri | http://hdl.handle.net/1885/57929 | |
dc.description.abstract | Recent advances in optimization theory have shown that smooth strongly convex finite sums can be minimized faster than by treating them as a black box "batch" problem. In this work we introduce a new method in this class with a theoretical convergence rate four times faster than ex-isting methods, for sums with sufficiently many terms. This method is also amendable to a sampling without replacement scheme that in practice gives further speed-ups. We give empirical results showing state of the art performance. | |
dc.publisher | JMLR | |
dc.relation.ispartofseries | 31st International Conference on Machine Learning, ICML 2014 | |
dc.source | 31st International Conference on Machine Learning, ICML 2014 | |
dc.title | Finito: A faster, permutable incremental gradient method for big data problems | |
dc.type | Conference paper | |
local.description.notes | Imported from ARIES | |
local.description.refereed | Yes | |
dc.date.issued | 2014 | |
local.identifier.absfor | 080104 - Computer Vision | |
local.identifier.absfor | 080109 - Pattern Recognition and Data Mining | |
local.identifier.absfor | 020100 - ASTRONOMICAL AND SPACE SCIENCES | |
local.identifier.ariespublication | a383154xPUB421 | |
local.type.status | Published Version | |
local.contributor.affiliation | Defazio, Aaron, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Caetano, Tiberio, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Domke, Justin, College of Engineering and Computer Science, ANU | |
local.description.embargo | 2037-12-31 | |
local.bibliographicCitation.startpage | 2839 | |
local.bibliographicCitation.lastpage | 2855 | |
local.identifier.absseo | 970108 - Expanding Knowledge in the Information and Computing Sciences | |
dc.date.updated | 2015-12-09T11:08:15Z | |
local.identifier.scopusID | 2-s2.0-84919829570 | |
Collections | ANU Research Publications |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Defazio_Finito:_A_faster,_permutable_2014.pdf | 2.09 MB | Adobe PDF | Request a copy |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator