Second order cone programming approaches for handling missing and uncertain data
Download (419.23 kB)
Shivaswamy, Pannagadatta; Bhattacharyya, Chiranjib; Smola, Alexander
Description
We propose a novel second order cone programming formulation for designing robust classifiers which can handle uncertainty in observations. Similar formulations are also derived for designing regression functions which are robust to uncertainties in the regression setting. The proposed formulations are independent of the underlying distribution, requiring only the existence of second order moments. These formulations are then specialized to the case of missing values in observations for...[Show more]
dc.contributor.author | Shivaswamy, Pannagadatta | |
---|---|---|
dc.contributor.author | Bhattacharyya, Chiranjib | |
dc.contributor.author | Smola, Alexander | |
dc.date.accessioned | 2009-05-22T01:30:18Z | |
dc.date.accessioned | 2010-12-20T06:05:04Z | |
dc.date.available | 2009-05-22T01:30:18Z | |
dc.date.available | 2010-12-20T06:05:04Z | |
dc.identifier.citation | Journal of Machine Learning Research 7.7 (2006): 1283-1314 | |
dc.identifier.issn | 1532-4435 | |
dc.identifier.issn | 1533-7928 | |
dc.identifier.uri | http://hdl.handle.net/10440/307 | |
dc.identifier.uri | http://digitalcollections.anu.edu.au/handle/10440/307 | |
dc.description.abstract | We propose a novel second order cone programming formulation for designing robust classifiers which can handle uncertainty in observations. Similar formulations are also derived for designing regression functions which are robust to uncertainties in the regression setting. The proposed formulations are independent of the underlying distribution, requiring only the existence of second order moments. These formulations are then specialized to the case of missing values in observations for both classification and regression problems. Experiments show that the proposed formulations outperform imputation. | |
dc.format | 32 pages | |
dc.publisher | MIT Press | |
dc.rights | http://www.sherpa.ac.uk/romeo/search.php "Author can archive pre-print (ie pre-refereeing) ... [but] cannot archive post-print (ie final draft post-refereeing) … [and] subject to Restrictions, 3 months for STM, author can archive publisher's version/PDF ... on institutional repository; Publisher copyright and source must be acknowledged; Must link to journal homepage; Publishers’ copyright statement must be included; Publisher's version/PDF must be used for post-print deposit." - from SHERPA/RoMEO site (as at 18/02/10) | |
dc.source | Journal of Machine Learning Research | |
dc.source.uri | http://jmlr.csail.mit.edu/papers/volume7/shivaswamy06a/shivaswamy06a.pdf | |
dc.subject | Keywords: Classification (of information); Data reduction; Method of moments; Problem solving; Regression analysis; Uncertain systems; Regression problems; Second order cone programming; Second order moments; Uncertain data; Computer systems programming | |
dc.title | Second order cone programming approaches for handling missing and uncertain data | |
dc.type | Journal article | |
local.identifier.citationvolume | 7 | |
dc.date.issued | 2006-07 | |
local.identifier.absfor | 080109 | |
local.identifier.ariespublication | u8803936xPUB35 | |
local.type.status | Published Version | |
local.contributor.affiliation | Shivaswamy, Pannagadatta, Indian Institute of Science | |
local.contributor.affiliation | Bhattacharyya, Chiranjib, Indian Institute of Science | |
local.contributor.affiliation | Smola, Alexander, Research School of Information Sciences and Engineering, Computer Sciences Laboratory | |
local.bibliographicCitation.issue | 7 | |
local.bibliographicCitation.startpage | 1283 | |
local.bibliographicCitation.lastpage | 1314 | |
dc.date.updated | 2015-12-08T03:29:21Z | |
local.identifier.scopusID | 2-s2.0-33745800909 | |
Collections | ANU Research Publications |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
Shivaswamy_Second2006.pdf | 419.23 kB | Adobe PDF |
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