Accurate On-line Support Vector Regression. Ma, J., Theiler, J., & Perkins, S. Neural Computation, 15(11):2683–2703, November, 2003. Conference Name: Neural Computationdoi abstract bibtex Batch implementations of support vector regression (SVR) are inefficient when used in an on-line setting because they must be retrained from scratch every time the training set is modified. Following an incremental support vector classification algorithm introduced by Cauwenberghs and Poggio (2001), we have developed an accurate on-line support vector regression (AOSVR) that efficiently updates a trained SVR function whenever a sample is added to or removed from the training set. The updated SVR function is identical to that produced by a batch algorithm. Applications of AOSVR in both on-line and cross-validation scenarios are presented.Inbothscenarios, numerical experiments indicate that AOSVR is faster than batch SVR algorithms with both cold and warm start.
@article{ma_accurate_2003,
title = {Accurate {On}-line {Support} {Vector} {Regression}},
volume = {15},
issn = {0899-7667},
doi = {10.1162/089976603322385117},
abstract = {Batch implementations of support vector regression (SVR) are inefficient when used in an on-line setting because they must be retrained from scratch every time the training set is modified. Following an incremental support vector classification algorithm introduced by Cauwenberghs and Poggio (2001), we have developed an accurate on-line support vector regression (AOSVR) that efficiently updates a trained SVR function whenever a sample is added to or removed from the training set. The updated SVR function is identical to that produced by a batch algorithm. Applications of AOSVR in both on-line and cross-validation scenarios are presented.Inbothscenarios, numerical experiments indicate that AOSVR is faster than batch SVR algorithms with both cold and warm start.},
number = {11},
journal = {Neural Computation},
author = {Ma, Junshui and Theiler, James and Perkins, Simon},
month = nov,
year = {2003},
note = {Conference Name: Neural Computation},
pages = {2683--2703},
}
Downloads: 0
{"_id":"fTDnnoL3RRwSZmFAv","bibbaseid":"ma-theiler-perkins-accurateonlinesupportvectorregression-2003","authorIDs":[],"author_short":["Ma, J.","Theiler, J.","Perkins, S."],"bibdata":{"bibtype":"article","type":"article","title":"Accurate On-line Support Vector Regression","volume":"15","issn":"0899-7667","doi":"10.1162/089976603322385117","abstract":"Batch implementations of support vector regression (SVR) are inefficient when used in an on-line setting because they must be retrained from scratch every time the training set is modified. Following an incremental support vector classification algorithm introduced by Cauwenberghs and Poggio (2001), we have developed an accurate on-line support vector regression (AOSVR) that efficiently updates a trained SVR function whenever a sample is added to or removed from the training set. The updated SVR function is identical to that produced by a batch algorithm. Applications of AOSVR in both on-line and cross-validation scenarios are presented.Inbothscenarios, numerical experiments indicate that AOSVR is faster than batch SVR algorithms with both cold and warm start.","number":"11","journal":"Neural Computation","author":[{"propositions":[],"lastnames":["Ma"],"firstnames":["Junshui"],"suffixes":[]},{"propositions":[],"lastnames":["Theiler"],"firstnames":["James"],"suffixes":[]},{"propositions":[],"lastnames":["Perkins"],"firstnames":["Simon"],"suffixes":[]}],"month":"November","year":"2003","note":"Conference Name: Neural Computation","pages":"2683–2703","bibtex":"@article{ma_accurate_2003,\n\ttitle = {Accurate {On}-line {Support} {Vector} {Regression}},\n\tvolume = {15},\n\tissn = {0899-7667},\n\tdoi = {10.1162/089976603322385117},\n\tabstract = {Batch implementations of support vector regression (SVR) are inefficient when used in an on-line setting because they must be retrained from scratch every time the training set is modified. Following an incremental support vector classification algorithm introduced by Cauwenberghs and Poggio (2001), we have developed an accurate on-line support vector regression (AOSVR) that efficiently updates a trained SVR function whenever a sample is added to or removed from the training set. The updated SVR function is identical to that produced by a batch algorithm. Applications of AOSVR in both on-line and cross-validation scenarios are presented.Inbothscenarios, numerical experiments indicate that AOSVR is faster than batch SVR algorithms with both cold and warm start.},\n\tnumber = {11},\n\tjournal = {Neural Computation},\n\tauthor = {Ma, Junshui and Theiler, James and Perkins, Simon},\n\tmonth = nov,\n\tyear = {2003},\n\tnote = {Conference Name: Neural Computation},\n\tpages = {2683--2703},\n}\n\n","author_short":["Ma, J.","Theiler, J.","Perkins, S."],"key":"ma_accurate_2003","id":"ma_accurate_2003","bibbaseid":"ma-theiler-perkins-accurateonlinesupportvectorregression-2003","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","creationDate":"2019-05-28T23:29:25.282Z","downloads":0,"keywords":[],"search_terms":["accurate","line","support","vector","regression","ma","theiler","perkins"],"title":"Accurate On-line Support Vector Regression","year":2003,"dataSources":["aDrN6vnZWqY8fA7E8","iwKepCrWBps7ojhDx"]}