Another look at distance-weighted discrimination
Distance-weighted discrimination (DWD) is a modern margin-based classifier with an interesting geometric motivation. It was proposed as a competitor to the support vector machine (SVM). Despite many recent references on DWD, DWD is far less popular than the SVM, mainly because of computational and t...
Uložené v:
| Vydané v: | Journal of the Royal Statistical Society. Series B, Statistical methodology Ročník 80; číslo 1; s. 177 - 198 |
|---|---|
| Hlavní autori: | , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Oxford
John Wiley & Sons Ltd
01.01.2018
Oxford University Press |
| Predmet: | |
| ISSN: | 1369-7412, 1467-9868 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Distance-weighted discrimination (DWD) is a modern margin-based classifier with an interesting geometric motivation. It was proposed as a competitor to the support vector machine (SVM). Despite many recent references on DWD, DWD is far less popular than the SVM, mainly because of computational and theoretical reasons. We greatly advance the current DWD methodology and its learning theory. We propose a novel thrifty algorithm for solving standard DWD and generalized DWD, and our algorithm can be several hundred times faster than the existing state of the art algorithm based on second-order cone programming. In addition, we exploit the new algorithm to design an efficient scheme to tune generalized DWD. Furthermore, we formulate a natural kernel DWD approach in a reproducing kernel Hubert space and then establish the Bayes risk consistency of the kernel DWD by using a universal kernel such as the Gaussian kernel. This result solves an open theoretical problem in the DWD literature. A comparison study on 16 benchmark data sets shows that data-driven generalized DWD consistently delivers higher classification accuracy with less computation time than the SVM. |
|---|---|
| AbstractList | Summary
Distance‐weighted discrimination (DWD) is a modern margin‐based classifier with an interesting geometric motivation. It was proposed as a competitor to the support vector machine (SVM). Despite many recent references on DWD, DWD is far less popular than the SVM, mainly because of computational and theoretical reasons. We greatly advance the current DWD methodology and its learning theory. We propose a novel thrifty algorithm for solving standard DWD and generalized DWD, and our algorithm can be several hundred times faster than the existing state of the art algorithm based on second‐order cone programming. In addition, we exploit the new algorithm to design an efficient scheme to tune generalized DWD. Furthermore, we formulate a natural kernel DWD approach in a reproducing kernel Hilbert space and then establish the Bayes risk consistency of the kernel DWD by using a universal kernel such as the Gaussian kernel. This result solves an open theoretical problem in the DWD literature. A comparison study on 16 benchmark data sets shows that data‐driven generalized DWD consistently delivers higher classification accuracy with less computation time than the SVM. Distance-weighted discrimination (DWD) is a modern margin-based classifier with an interesting geometric motivation. It was proposed as a competitor to the support vector machine (SVM). Despite many recent references on DWD, DWD is far less popular than the SVM, mainly because of computational and theoretical reasons. We greatly advance the current DWD methodology and its learning theory. We propose a novel thrifty algorithm for solving standard DWD and generalized DWD, and our algorithm can be several hundred times faster than the existing state of the art algorithm based on second-order cone programming. In addition, we exploit the new algorithm to design an efficient scheme to tune generalized DWD. Furthermore, we formulate a natural kernel DWD approach in a reproducing kernel Hilbert space and then establish the Bayes risk consistency of the kernel DWD by using a universal kernel such as the Gaussian kernel. This result solves an open theoretical problem in the DWD literature. A comparison study on 16 benchmark data sets shows that data-driven generalized DWD consistently delivers higher classification accuracy with less computation time than the SVM. Distance-weighted discrimination (DWD) is a modern margin-based classifier with an interesting geometric motivation. It was proposed as a competitor to the support vector machine (SVM). Despite many recent references on DWD, DWD is far less popular than the SVM, mainly because of computational and theoretical reasons. We greatly advance the current DWD methodology and its learning theory. We propose a novel thrifty algorithm for solving standard DWD and generalized DWD, and our algorithm can be several hundred times faster than the existing state of the art algorithm based on second-order cone programming. In addition, we exploit the new algorithm to design an efficient scheme to tune generalized DWD. Furthermore, we formulate a natural kernel DWD approach in a reproducing kernel Hubert space and then establish the Bayes risk consistency of the kernel DWD by using a universal kernel such as the Gaussian kernel. This result solves an open theoretical problem in the DWD literature. A comparison study on 16 benchmark data sets shows that data-driven generalized DWD consistently delivers higher classification accuracy with less computation time than the SVM. |
| Author | Zou, Hui Wang, Boxiang |
| Author_xml | – sequence: 1 givenname: Boxiang surname: Wang fullname: Wang, Boxiang – sequence: 2 givenname: Hui surname: Zou fullname: Zou, Hui |
| BookMark | eNp9kE1LAzEQhoNUsK1evAsFLyJsTbLZfBxr8QsKgtVzyKaJ3brd1CSl9N-bdtVDEeeSMDzPMPP2QKdxjQHgHMEhSnXjQyiHCGNCjkAXEcoywSnvpH9ORcYIwiegF8ICpqIs7wI4alycGz-onfsYqDiYVSGqRptsY6r3eTSzXUf7alk1KlauOQXHVtXBnH2_ffB2f_c6fswmzw9P49Ek0zkXJFOlxhSXWBlkRUGggooX3FJeCoxmvNCEWaEwNDlFxkBaUl1oM4OYldYyS_I-uGrnrrz7XJsQ5TLtYepaNcatg8QQQ04JYzihlwfowq19k7aTSDCOCgQRT9R1S2nvQvDGylW6SvmtRFDuwpO78OQ-vATDA1hXcX9_9Kqq_1ZQq2yq2mz_GS5fptPbH-eidRYhOv_rEEI5YkLkXwlNjLU |
| CitedBy_id | crossref_primary_10_1080_00401706_2018_1529629 crossref_primary_10_1002_sta4_598 crossref_primary_10_1007_s00180_023_01448_z crossref_primary_10_1016_j_neunet_2022_10_017 crossref_primary_10_1016_j_engappai_2022_104828 crossref_primary_10_1111_sjos_12484 crossref_primary_10_1016_j_knosys_2019_105420 crossref_primary_10_1002_wcms_70042 crossref_primary_10_1137_18M1202311 crossref_primary_10_1080_01621459_2024_2403788 crossref_primary_10_1088_1742_5468_abbed5 crossref_primary_10_1016_j_annonc_2024_12_010 crossref_primary_10_1038_s43856_025_00945_0 crossref_primary_10_3390_math12060855 crossref_primary_10_1080_10618600_2022_2138407 crossref_primary_10_3390_e22111257 crossref_primary_10_1016_j_neucom_2020_12_110 crossref_primary_10_1088_1742_5468_ac2edd crossref_primary_10_1002_nla_2299 crossref_primary_10_1016_j_patcog_2019_107030 crossref_primary_10_1016_j_jco_2025_101931 crossref_primary_10_1080_10618600_2022_2069778 crossref_primary_10_1080_10618600_2017_1366915 crossref_primary_10_1007_s10107_019_01423_x crossref_primary_10_1287_opre_2021_2115 crossref_primary_10_1016_j_patcog_2022_108828 |
| Cites_doi | 10.1198/0003130042836 10.1017/CBO9780511624216 10.1198/016214505000000907 10.1080/10618600.2012.700878 10.1002/wics.1345 10.1198/016214507000001120 10.4310/SII.2015.v8.n3.a7 10.1007/978-0-387-21706-2 10.1007/s10107-002-0339-5 10.1016/j.spl.2004.03.002 10.1093/bioinformatics/bts096 10.1007/978-1-4757-2440-0 10.1214/aos/1079120130 10.1198/jcgs.2010.09014 10.1198/jasa.2010.tm08487 10.1198/jasa.2011.tm10319 10.1214/009053605000000200 10.1080/10618600.2015.1049700 10.1017/CBO9780511804441 10.1023/A:1012406528296 10.1006/jcss.1997.1504 10.1080/10618600.2000.10474858 10.1111/j.1467-9868.2005.00510.x 10.1007/s10107-016-1007-5 10.1023/A:1015469627679 10.1007/s10107-012-0612-1 10.1007/s10107-014-0850-5 10.1007/978-0-387-84858-7 10.1214/08-STS264 10.1080/10618600.2012.680324 10.1198/106186005X25619 10.1137/1.9781611970128 10.1023/A:1010933404324 |
| ContentType | Journal Article |
| Copyright | Copyright © 2018 The Royal Statistical Society and Blackwell Publishing Ltd. 2017 Royal Statistical Society Copyright © 2018 The Royal Statistical Society and Blackwell Publishing Ltd |
| Copyright_xml | – notice: Copyright © 2018 The Royal Statistical Society and Blackwell Publishing Ltd. – notice: 2017 Royal Statistical Society – notice: Copyright © 2018 The Royal Statistical Society and Blackwell Publishing Ltd |
| DBID | AAYXX CITATION 7SC 8BJ 8FD FQK JBE JQ2 L7M L~C L~D 7S9 L.6 |
| DOI | 10.1111/rssb.12244 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts International Bibliography of the Social Sciences (IBSS) Technology Research Database International Bibliography of the Social Sciences International Bibliography of the Social Sciences ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef International Bibliography of the Social Sciences (IBSS) Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | CrossRef International Bibliography of the Social Sciences (IBSS) AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Statistics |
| EISSN | 1467-9868 |
| EndPage | 198 |
| ExternalDocumentID | 10_1111_rssb_12244 RSSB12244 44681799 |
| Genre | article |
| GrantInformation_xml | – fundername: National Science Foundation funderid: DMS‐1505111 |
| GroupedDBID | -~X .3N .4S .DC .GA 05W 10A 1OC 29L 2AX 33P 3SF 4.4 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 5GY 5HH 5LA 5VS 66C 702 7PT 8-0 8-1 8-3 8UM 8VB 930 A03 AAESR AAEVG AAHBH AAONW AAPXW AASGY AAUAY AAWIL AAXRX AAZKR ABAWQ ABBHK ABCQN ABCUV ABDFA ABEHJ ABEML ABFAN ABIVO ABLJU ABPFR ABPQH ABPQP ABPTD ABPVW ABWST ABXSQ ABYWD ABZEH ACAHQ ACCZN ACGFS ACHJO ACIWK ACMTB ACNCT ACPOU ACSCC ACTMH ACUBG ACXBN ACXQS ADBBV ADEOM ADIYS ADIZJ ADKYN ADMGS ADODI ADOZA ADRDM ADVEK ADZMN AEGXH AEIMD AEMOZ AEUPB AFBPY AFEBI AFGKR AFVYC AFXHP AFZJQ AGLNM AHQJS AIHAF AIURR AJAOE AJNCP AJXKR AKVCP ALAGY ALMA_UNASSIGNED_HOLDINGS ALRMG ALUQN AMBMR AMVHM AMYDB ARCSS ASPBG ATUGU AUFTA AVWKF AZBYB AZVAB BAFTC BCRHZ BDRZF BHBCM BMNLL BMXJE BNHUX BROTX BRXPI BY8 CAG CJ0 CO8 CS3 D-E DCZOG DPXWK DQDLB DR2 DRFUL DRSTM DSRWC EBA EBO EBR EBS EBU ECEWR EDO EJD EMK F00 F5P G-S G.N GODZA H.T H.X HQ6 HZI HZ~ IHE IPSME IX1 J0M JAAYA JAS JBMMH JBZCM JENOY JHFFW JKQEH JLEZI JLXEF JMS JPL JST K1G K48 LATKE LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MK4 MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 NF~ NU- O66 O9- OIG P2W P2X P4D PQQKQ Q.N Q11 QB0 QWB R.K RNS ROL ROX RX1 SA0 SUPJJ TH9 TN5 TUS UB1 UPT W8V W99 WBKPD WH7 WIH WIK WOHZO WQJ WYISQ XBAML XG1 YQT ZL0 ZZTAW ~02 ~IA ~KM ~WT .Y3 3-9 31~ AAHHS AANHP AARHZ ABYAD ACBWZ ACCFJ ACFRR ACRPL ACTWD ACYXJ ADNMO ADQBN ADULT AEEZP AELPN AEQDE AEUQT AFPWT AIWBW AJBDE ANFBD AS~ ATGXG AZFZN COF FEDTE FVMVE H13 HF~ HGD HVGLF H~9 JSODD NHB RJQFR ZGI AAYXX ABEJV CITATION O8X OJZSN 7SC 8BJ 8FD FQK JBE JQ2 L7M L~C L~D 7S9 L.6 |
| ID | FETCH-LOGICAL-c3894-abc262b2ae1f9540a0a858f68b921d85c47f9a20e361ee06b6c5ced027bff7f43 |
| IEDL.DBID | DRFUL |
| ISICitedReferencesCount | 35 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000418339600009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1369-7412 |
| IngestDate | Fri Oct 03 00:08:58 EDT 2025 Mon Nov 10 00:42:49 EST 2025 Tue Nov 18 21:16:41 EST 2025 Sat Nov 29 05:52:03 EST 2025 Wed Jan 22 16:29:34 EST 2025 Thu Jul 03 22:07:11 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| License | https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3894-abc262b2ae1f9540a0a858f68b921d85c47f9a20e361ee06b6c5ced027bff7f43 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| PQID | 1978151018 |
| PQPubID | 39359 |
| PageCount | 22 |
| ParticipantIDs | proquest_miscellaneous_2020864772 proquest_journals_1978151018 crossref_primary_10_1111_rssb_12244 crossref_citationtrail_10_1111_rssb_12244 wiley_primary_10_1111_rssb_12244_RSSB12244 jstor_primary_44681799 |
| PublicationCentury | 2000 |
| PublicationDate | 20180101 January 2018 2018-01-01 |
| PublicationDateYYYYMMDD | 2018-01-01 |
| PublicationDate_xml | – month: 1 year: 2018 text: 20180101 day: 1 |
| PublicationDecade | 2010 |
| PublicationPlace | Oxford |
| PublicationPlace_xml | – name: Oxford |
| PublicationTitle | Journal of the Royal Statistical Society. Series B, Statistical methodology |
| PublicationYear | 2018 |
| Publisher | John Wiley & Sons Ltd Oxford University Press |
| Publisher_xml | – name: John Wiley & Sons Ltd – name: Oxford University Press |
| References | 2007; 102 2013; 22 2010; 19 2010; 105 2000; 9 2004; 68 2008; 36 2001; 45 2005; 67 1977 1994; 20 2004; 32 2010; 25 1997; 55 1990 2000 2002; 46 2015a; 8 2014; 15 1999; 12 2016; 155 2017; 161 2012; 28 2005; 33 2015; 16 2002; 6 2009 2006; 7 1998 2002; 2 1995 1964; 25 2004 2002 1999; 6 2015; 7 1999 2004; 11 2004; 95 2011; 106 2004; 58 2015b; 16 2017 2015 2001; 2 2014 2013 2014; 143 2006; 101 2016; 25 2005; 14 Hastie (2023022101111704700_) 2009 Vapnik (2023022101111704700_) 1998 Hunter (2023022101111704700_) 2004; 58 Lichman (2023022101111704700_) 2013 Vapnik (2023022101111704700_) 1995 Zhou (2023022101111704700_) 2010; 19 Meyer (2023022101111704700_) 2015 Bartlett (2023022101111704700_) 1999 Zhu (2023022101111704700_) 2005; 14 Liaw (2023022101111704700_) 2002; 2 Bartlett (2023022101111704700_) 2006; 101 Liu (2023022101111704700_) 2011; 106 Qiao (2023022101111704700_) 2010; 105 Qiao (2023022101111704700_) 2015; 8 Hall (2023022101111704700_) 2005; 67 Lin (2023022101111704700_) 2002; 46 Lam (2023022101111704700_) 2017 Marron (2023022101111704700_) 2013 Alizadeh (2023022101111704700_) 2004; 95 Chen (2023022101111704700_) 2017; 161 Lange (2023022101111704700_) 2014; 143 Marron (2023022101111704700_) 2015; 7 Yang (2023022101111704700_) 2013; 22 Shawe-Taylor (2023022101111704700_) 2000 Zhang (2023022101111704700_) 2004; 32 Platt (2023022101111704700_) 1999; 12 Wang (2023022101111704700_) 2016; 25 Qiao (2023022101111704700_) 2015; 16 Hunter (2023022101111704700_) 2005; 33 Micchelli (2023022101111704700_) 2006; 7 Zou (2023022101111704700_) 2008; 36 Freund (2023022101111704700_) 1997; 55 Steinwart (2023022101111704700_) 2001; 2 Huang (2023022101111704700_) 2013; 22 Wahba (2023022101111704700_) 1990 Anthony (2023022101111704700_) 1999 Chen (2023022101111704700_) 2015 Lin (2023022101111704700_) 2004; 68 Zhang (2023022101111704700_) 2015; 16 Venables (2023022101111704700_) 2002 Lin (2023022101111704700_) 2002; 6 Karatzoglou (2023022101111704700_) 2004; 11 Marron (2023022101111704700_) 2007; 102 Hsieh (2023022101111704700_) 2014 Breiman (2023022101111704700_) 2001; 45 Jaakkola (2023022101111704700_) 1999 Wu (2023022101111704700_) 2010; 25 De Leeuw (2023022101111704700_) 1977 Li (2023022101111704700_) 2016; 155 Fernández-Delgado (2023022101111704700_) 2014; 15 Wahba (2023022101111704700_) 1994; 20 Huang (2023022101111704700_) 2012; 28 Wahba (2023022101111704700_) 1999; 6 Aizerman (2023022101111704700_) 1964; 25 Ridgeway (2023022101111704700_) 2017 Boyd (2023022101111704700_) 2004 Lange (2023022101111704700_) 2000; 9 |
| References_xml | – volume: 11 start-page: 1 year: 2004 end-page: 20 article-title: kernlab—an S4 package for kernel methods in R publication-title: J. Statist. Softwr. – volume: 16 start-page: 1547 year: 2015b end-page: 1572 article-title: Flexible high‐dimensional classification machines and their asymptotic properties publication-title: J. Mach. Learn. Res. – volume: 2 start-page: 67 year: 2001 end-page: 93 article-title: On the influence of the kernel on the consistency of support vector machines publication-title: J. Mach. Learn. Res. – year: 2009 – volume: 155 start-page: 333 year: 2016 end-page: 373 article-title: A Schur complement based semi‐proximal ADMM for convex quadratic conic programming and extensions publication-title: Math. Programmng – volume: 9 start-page: 1 year: 2000 end-page: 20 article-title: Optimization transfer using surrogate objective functions publication-title: J. Computnl Graph. Statist. – start-page: 566 year: 2014 end-page: 574 – volume: 25 start-page: 821 year: 1964 end-page: 837 article-title: Theoretical foundations of the potential function method in pattern recognition learning publication-title: Automn Remote Control – volume: 46 start-page: 191 year: 2002 end-page: 202 article-title: Support vector machines for classification in nonstandard situations publication-title: Mach. Learn. – volume: 106 start-page: 166 year: 2011 end-page: 177 article-title: Hard or soft classification?: Large‐margin unified machines publication-title: J. Am. Statist. Ass. – volume: 12 start-page: 185 year: 1999 end-page: 208 article-title: Fast training of support vector machines using sequential minimal optimization publication-title: Advances in Kernel Methods—Support Vector Learning – volume: 19 start-page: 645 year: 2010 end-page: 665 article-title: MM algorithms for some discrete multivariate distributions publication-title: J. Computnl Graph. Statist. – year: 1990 – year: 1998 – volume: 102 start-page: 1267 year: 2007 end-page: 1271 article-title: Distance weighted discrimination publication-title: J. Am. Statist. Ass. – volume: 55 start-page: 119 year: 1997 end-page: 139 article-title: A decision‐theoretic generalization of on‐line learning and an application to boosting publication-title: J. Comput. Syst. Sci. – volume: 101 start-page: 138 year: 2006 end-page: 156 article-title: Convexity, classification, and risk bounds publication-title: J. Am. Statist. Ass. – volume: 7 start-page: 2651 year: 2006 end-page: 2667 article-title: Universal kernels publication-title: J. Mach. Learn. Res. – volume: 6 start-page: 259 year: 2002 end-page: 275 article-title: Support vector machines and the Bayes rule in classification publication-title: Data Minng Knowl. Discov. – year: 2004 – volume: 15 start-page: 3133 year: 2014 end-page: 3181 article-title: Do we need hundreds of classifiers to solve real world classification problems? publication-title: J. Mach. Learn. Res. – volume: 22 start-page: 396 year: 2013 end-page: 415 article-title: An efficient algorithm for computing the HHSVM and its generalizations publication-title: J. Computnl Graph. Statist. – volume: 2 start-page: 18 year: 2002 end-page: 22 article-title: Classification and regression by randomForest publication-title: R News – year: 1999 article-title: Probabilistic kernel regression models publication-title: Proc. 7th Int. Wrkshp Artificial Intelligence and Statistics – year: 2015 – volume: 25 start-page: 492 year: 2010 end-page: 505 article-title: The MM alternative to EM publication-title: Statist. Sci. – volume: 14 start-page: 185 year: 2005 end-page: 205 article-title: Kernel logistic regression and the import vector machine publication-title: J. Computnl Graph. Statist. – volume: 22 start-page: 953 year: 2013 end-page: 969 article-title: Multiclass distance‐weighted discrimination publication-title: J. Computnl Graph. Statist. – volume: 28 start-page: 1182 year: 2012 end-page: 1183 article-title: R/DWD: distance‐weighted discrimination for classification, visualization and batch adjustment publication-title: Bioinformatics – volume: 32 start-page: 56 year: 2004 end-page: 134 article-title: Statistical behavior and consistency of classification methods based on convex risk minimization publication-title: Ann. Statist. – volume: 25 start-page: 826 year: 2016 end-page: 838 article-title: Sparse distance weighted discrimination publication-title: J. Computnl Graph. Statist. – volume: 16 start-page: 3299 year: 2015 end-page: 3340 article-title: Divide and conquer kernel ridge regression: a distributed algorithm with minimax optimal rates publication-title: J. Mach. Learn. Res. – volume: 6 start-page: 69 year: 1999 end-page: 87 article-title: Support vector machines, reproducing kernel Hilbert spaces and the randomized GACV publication-title: Advances in Kernel Methods–Support Vector Learning – volume: 8 start-page: 331 year: 2015a end-page: 345 article-title: Distance‐weighted support vector machine publication-title: Statist. Interfc. – volume: 7 start-page: 109 year: 2015 end-page: 114 article-title: Distance‐weighted discrimination publication-title: Wiley Interdisc. Rev. Computnl Statist. – volume: 67 start-page: 427 year: 2005 end-page: 444 article-title: Geometric representation of high dimension, low sample size data publication-title: J. R. Statist. Soc. – volume: 45 start-page: 5 year: 2001 end-page: 32 article-title: Random forests publication-title: Mach. Learn. – volume: 58 start-page: 30 year: 2004 end-page: 37 article-title: A tutorial on MM algorithms publication-title: Am. Statistn – volume: 143 start-page: 339 year: 2014 end-page: 356 article-title: MM algorithms for geometric and signomial programming publication-title: Math. Programmng – volume: 95 start-page: 3 year: 2004 end-page: 51 article-title: Second‐order cone programming publication-title: Math. Programmng – year: 2002 – start-page: 43 year: 1999 end-page: 54 – volume: 161 start-page: 237 year: 2017 end-page: 270 article-title: An efficient inexact symmetric Gauss‐Seidel based majorized ADMM for high‐dimensional convex composite conic programming publication-title: Math. Programmng – volume: 36 start-page: 1509 year: 2008 end-page: 1533 article-title: One‐step sparse estimates in nonconcave penalized likelihood models publication-title: Ann. Statist. – year: 1995 – volume: 68 start-page: 73 year: 2004 end-page: 82 article-title: A note on margin‐based loss functions in classification publication-title: Statist. Probab. Lett. – volume: 20 start-page: 313 year: 1994 end-page: 331 article-title: Soft classification, aka risk estimation, via penalized log likelihood and smoothing spline analysis of variance publication-title: Santa Fe Institute Studies in the Sciences of Complexity Proc. – volume: 33 start-page: 1617 year: 2005 end-page: 1642 article-title: Variable selection using MM algorithms publication-title: Ann. Statist. – year: 2017 – start-page: 735 year: 1977 end-page: 752 – volume: 105 start-page: 401 year: 2010 end-page: 414 article-title: Weighted distance weighted discrimination and its asymptotic properties publication-title: J. Am. Statist. Ass. – start-page: 349 year: 2000 end-page: 358 – year: 1999 – year: 2013 – volume: 12 start-page: 185 year: 1999 ident: 2023022101111704700_ article-title: Fast training of support vector machines using sequential minimal optimization publication-title: Advances in Kernel Methods—Support Vector Learning – volume-title: Fast algorithms for large scale generalized distance weighted discrimination year: 2017 ident: 2023022101111704700_ – year: 2015 ident: 2023022101111704700_ – volume-title: gbm: generalized boosted regression models year: 2017 ident: 2023022101111704700_ – volume: 58 start-page: 30 year: 2004 ident: 2023022101111704700_ article-title: A tutorial on MM algorithms publication-title: Am. Statistn doi: 10.1198/0003130042836 – volume-title: Neural Network Learning: Theoretical Foundations year: 1999 ident: 2023022101111704700_ doi: 10.1017/CBO9780511624216 – volume: 101 start-page: 138 year: 2006 ident: 2023022101111704700_ article-title: Convexity, classification, and risk bounds publication-title: J. Am. Statist. Ass. doi: 10.1198/016214505000000907 – volume: 20 start-page: 313 year: 1994 ident: 2023022101111704700_ article-title: Soft classification, aka risk estimation, via penalized log likelihood and smoothing spline analysis of variance publication-title: Santa Fe Institute Studies in the Sciences of Complexity Proc. – volume: 22 start-page: 953 year: 2013 ident: 2023022101111704700_ article-title: Multiclass distance-weighted discrimination publication-title: J. Computnl Graph. Statist. doi: 10.1080/10618600.2012.700878 – volume: 7 start-page: 109 year: 2015 ident: 2023022101111704700_ article-title: Distance-weighted discrimination publication-title: Wiley Interdisc. Rev. Computnl Statist. doi: 10.1002/wics.1345 – volume: 102 start-page: 1267 year: 2007 ident: 2023022101111704700_ article-title: Distance weighted discrimination publication-title: J. Am. Statist. Ass. doi: 10.1198/016214507000001120 – volume-title: Mxnet: a flexible and efficient machine learning library for heterogeneous distributed systems year: 2015 ident: 2023022101111704700_ – volume: 8 start-page: 331 year: 2015 ident: 2023022101111704700_ article-title: Distance-weighted support vector machine publication-title: Statist. Interfc. doi: 10.4310/SII.2015.v8.n3.a7 – start-page: 735 volume-title: Convergence of correction matrix algorithms for multidimensional scaling. year: 1977 ident: 2023022101111704700_ – volume-title: Modern Applied Statistics with S year: 2002 ident: 2023022101111704700_ doi: 10.1007/978-0-387-21706-2 – volume: 6 start-page: 69 year: 1999 ident: 2023022101111704700_ article-title: Support vector machines, reproducing kernel Hilbert spaces and the randomized GACV publication-title: Advances in Kernel Methods–Support Vector Learning – volume: 95 start-page: 3 year: 2004 ident: 2023022101111704700_ article-title: Second-order cone programming publication-title: Math. Programmng doi: 10.1007/s10107-002-0339-5 – volume: 15 start-page: 3133 year: 2014 ident: 2023022101111704700_ article-title: Do we need hundreds of classifiers to solve real world classification problems? publication-title: J. Mach. Learn. Res. – volume: 68 start-page: 73 year: 2004 ident: 2023022101111704700_ article-title: A note on margin-based loss functions in classification publication-title: Statist. Probab. Lett. doi: 10.1016/j.spl.2004.03.002 – volume: 28 start-page: 1182 year: 2012 ident: 2023022101111704700_ article-title: R/DWD: distance-weighted discrimination for classification, visualization and batch adjustment publication-title: Bioinformatics doi: 10.1093/bioinformatics/bts096 – volume: 2 start-page: 67 year: 2001 ident: 2023022101111704700_ article-title: On the influence of the kernel on the consistency of support vector machines publication-title: J. Mach. Learn. Res. – year: 1999 ident: 2023022101111704700_ article-title: Probabilistic kernel regression models publication-title: Proc. 7th Int. Wrkshp Artificial Intelligence and Statistics – volume-title: The Nature of Statistical Learning Theory year: 1995 ident: 2023022101111704700_ doi: 10.1007/978-1-4757-2440-0 – volume: 32 start-page: 56 year: 2004 ident: 2023022101111704700_ article-title: Statistical behavior and consistency of classification methods based on convex risk minimization publication-title: Ann. Statist. doi: 10.1214/aos/1079120130 – volume: 19 start-page: 645 year: 2010 ident: 2023022101111704700_ article-title: MM algorithms for some discrete multivariate distributions publication-title: J. Computnl Graph. Statist. doi: 10.1198/jcgs.2010.09014 – volume: 2 start-page: 18 year: 2002 ident: 2023022101111704700_ article-title: Classification and regression by randomForest publication-title: R News – volume: 105 start-page: 401 year: 2010 ident: 2023022101111704700_ article-title: Weighted distance weighted discrimination and its asymptotic properties publication-title: J. Am. Statist. Ass. doi: 10.1198/jasa.2010.tm08487 – start-page: 349 volume-title: Advances in Kernel Methods—Support Vector Learning year: 2000 ident: 2023022101111704700_ – volume: 106 start-page: 166 year: 2011 ident: 2023022101111704700_ article-title: Hard or soft classification?: Large-margin unified machines publication-title: J. Am. Statist. Ass. doi: 10.1198/jasa.2011.tm10319 – volume: 33 start-page: 1617 year: 2005 ident: 2023022101111704700_ article-title: Variable selection using MM algorithms publication-title: Ann. Statist. doi: 10.1214/009053605000000200 – start-page: 43 volume-title: Advances in Kernel Methods–Support Vector Learning year: 1999 ident: 2023022101111704700_ – volume: 25 start-page: 826 year: 2016 ident: 2023022101111704700_ article-title: Sparse distance weighted discrimination publication-title: J. Computnl Graph. Statist. doi: 10.1080/10618600.2015.1049700 – volume: 7 start-page: 2651 year: 2006 ident: 2023022101111704700_ article-title: Universal kernels publication-title: J. Mach. Learn. Res. – start-page: 566 volume-title: Proc. Int. Conf. Machine Learning year: 2014 ident: 2023022101111704700_ – volume-title: UCI Machine Learning Repository year: 2013 ident: 2023022101111704700_ – volume-title: Smoothing, functional data analysis, and distance weighted discrimination software year: 2013 ident: 2023022101111704700_ – volume-title: Convex Optimization year: 2004 ident: 2023022101111704700_ doi: 10.1017/CBO9780511804441 – volume: 16 start-page: 1547 year: 2015 ident: 2023022101111704700_ article-title: Flexible high-dimensional classification machines and their asymptotic properties publication-title: J. Mach. Learn. Res. – volume: 16 start-page: 3299 year: 2015 ident: 2023022101111704700_ article-title: Divide and conquer kernel ridge regression: a distributed algorithm with minimax optimal rates publication-title: J. Mach. Learn. Res. – volume: 46 start-page: 191 year: 2002 ident: 2023022101111704700_ article-title: Support vector machines for classification in nonstandard situations publication-title: Mach. Learn. doi: 10.1023/A:1012406528296 – volume: 25 start-page: 821 year: 1964 ident: 2023022101111704700_ article-title: Theoretical foundations of the potential function method in pattern recognition learning publication-title: Automn Remote Control – volume: 55 start-page: 119 year: 1997 ident: 2023022101111704700_ article-title: A decision-theoretic generalization of on-line learning and an application to boosting publication-title: J. Comput. Syst. Sci. doi: 10.1006/jcss.1997.1504 – volume: 11 start-page: 1 year: 2004 ident: 2023022101111704700_ article-title: kernlab—an S4 package for kernel methods in R publication-title: J. Statist. Softwr. – volume: 9 start-page: 1 year: 2000 ident: 2023022101111704700_ article-title: Optimization transfer using surrogate objective functions publication-title: J. Computnl Graph. Statist. doi: 10.1080/10618600.2000.10474858 – volume: 67 start-page: 427 year: 2005 ident: 2023022101111704700_ article-title: Geometric representation of high dimension, low sample size data publication-title: J. R. Statist. Soc. doi: 10.1111/j.1467-9868.2005.00510.x – volume: 161 start-page: 237 year: 2017 ident: 2023022101111704700_ article-title: An efficient inexact symmetric Gauss-Seidel based majorized ADMM for high-dimensional convex composite conic programming publication-title: Math. Programmng doi: 10.1007/s10107-016-1007-5 – volume: 6 start-page: 259 year: 2002 ident: 2023022101111704700_ article-title: Support vector machines and the Bayes rule in classification publication-title: Data Minng Knowl. Discov. doi: 10.1023/A:1015469627679 – volume: 143 start-page: 339 year: 2014 ident: 2023022101111704700_ article-title: MM algorithms for geometric and signomial programming publication-title: Math. Programmng doi: 10.1007/s10107-012-0612-1 – volume-title: Statistical Learning Theory year: 1998 ident: 2023022101111704700_ – volume: 155 start-page: 333 year: 2016 ident: 2023022101111704700_ article-title: A Schur complement based semi-proximal ADMM for convex quadratic conic programming and extensions publication-title: Math. Programmng doi: 10.1007/s10107-014-0850-5 – volume: 36 start-page: 1509 year: 2008 ident: 2023022101111704700_ article-title: One-step sparse estimates in nonconcave penalized likelihood models publication-title: Ann. Statist. – volume-title: The Elements of Statistical Learning: Prediction, Inference, and Data Mining year: 2009 ident: 2023022101111704700_ doi: 10.1007/978-0-387-84858-7 – volume: 25 start-page: 492 year: 2010 ident: 2023022101111704700_ article-title: The MM alternative to EM publication-title: Statist. Sci. doi: 10.1214/08-STS264 – volume: 22 start-page: 396 year: 2013 ident: 2023022101111704700_ article-title: An efficient algorithm for computing the HHSVM and its generalizations publication-title: J. Computnl Graph. Statist. doi: 10.1080/10618600.2012.680324 – volume: 14 start-page: 185 year: 2005 ident: 2023022101111704700_ article-title: Kernel logistic regression and the import vector machine publication-title: J. Computnl Graph. Statist. doi: 10.1198/106186005X25619 – volume-title: Spline Models for Observational Data year: 1990 ident: 2023022101111704700_ doi: 10.1137/1.9781611970128 – volume: 45 start-page: 5 year: 2001 ident: 2023022101111704700_ article-title: Random forests publication-title: Mach. Learn. doi: 10.1023/A:1010933404324 |
| SSID | ssj0000673 |
| Score | 2.383777 |
| Snippet | Distance-weighted discrimination (DWD) is a modern margin-based classifier with an interesting geometric motivation. It was proposed as a competitor to the... Summary Distance‐weighted discrimination (DWD) is a modern margin‐based classifier with an interesting geometric motivation. It was proposed as a competitor to... Distance‐weighted discrimination (DWD) is a modern margin‐based classifier with an interesting geometric motivation. It was proposed as a competitor to the... |
| SourceID | proquest crossref wiley jstor |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 177 |
| SubjectTerms | Algorithms Bayes risk consistency Bayesian analysis Classification Classifiers Computation data collection Discrimination Distance‐weighted discrimination equations Hilbert space Kernel learning Learning Learning theories Learning theory Machine learning Majorization–minimization principle Motivation Novels Regression analysis risk Second‐order cone programming Statistical methods Statistics Support vector machines |
| Title | Another look at distance-weighted discrimination |
| URI | https://www.jstor.org/stable/44681799 https://onlinelibrary.wiley.com/doi/abs/10.1111%2Frssb.12244 https://www.proquest.com/docview/1978151018 https://www.proquest.com/docview/2020864772 |
| Volume | 80 |
| WOSCitedRecordID | wos000418339600009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1467-9868 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000673 issn: 1369-7412 databaseCode: DRFUL dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5q66EX38VolYheFCLJJptswIuv4qEUaa30FrKvU0mlafXqT_A3-kvc3aSxBRHEW0gmJMxj95vZ3W8AzmIaR5S70kGYUyfwuXAoFtKhKPYEYi7ipg_Zczfq9choFD_W4GpxFqbgh6gKbjoyzHitAzyl-VKQT_OcXup1oWANGkg5Lq5D467fGXaXR2K_OHcVO2rmRCU9qd7J8_32yoRU7ElcQZvLmNVMOp3N__3uFmyUYNO-LrxjG2oi24GmxpcFPfMuIJX-awhojxXYttOZzTWeVI7w-f7xZqqmgut7rOj-pa24B8PO_dPtg1O2UXCYQiOBk1KGQkRRKjwZK4CWuinBRIaExsjjBLMgknGKXOGHnhBuSEOGmeAqX6VSRjLwW1DPJpnYB5uqZDoQCoIoTB5gjggJsfR9xF0spRr7LDhf6DJhJce4bnUxTha5hlZDYtRgwWkl-1Iwa_wo1TImqURU-ko0i50F7YWNkjLs8sTTDF6GhMyCk-qxChi9CpJmYjLPE6Tbkurjt8iCC2OxXz6f9AeDG3N18BfhQ2gqYEWKUk0b6rPpXBzBOntV5p0el276BeiL62w |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB60CvbiuxitGtGLQiTZPLo51kepWIu0Kt5C9nUqqfShV3-Cv9Ff4s4mrS2IIN5CMiFhZ2b3m9mdbwBOYhbXmHCVQ0LBnMAX0mGhVA4jsScJd4kwfcieWrV2mz4_x_fF2Ryshcn5IaYJN_QMM1-jg2NCesbLB8MhO8eNoWARlgJtR9rAl646jcfW7FTs54VXsaOXTlLwk-JRnu-351ak_FDiHNycBa1m1Wms_fN_12G1gJt2PbePDViQ2SaUEWHmBM1bQOqZKcKyexpu2-nIFogotSl8vn-8mbypFHiP5_2_UI_b8Ni4frhsOkUjBYdrPBI4KeMkIoyk0lOxhmipm9KQqoiymHiChjyoqTglrvQjT0o3YhEPuRQ6YmVK1VTgV6CU9TO5AzbT4XQgNQjRqDwIBaE0CpXvE-GGSunZz4LTyWAmvGAZx2YXvWQSbeAwJGYYLDieyr7k3Bo_SlWMTqYiOoClyGNnQXWipKRwvGHiIYeXoSGz4Gj6WLsM7oOkmeyPhwnBxqRYgEssODMq--XzSafbvTBXu38RPoSV5sNdK2ndtG_3oKxhFs0TN1UojQZjuQ_L_FWrenBQ2OwXAyfvXA |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB60ivTiuxitGtGLQiTZPLo5VmtRLKW0Kt5C9nUqaelDr_4Ef6O_xJ1NWiuIIN5CMiFhZ2fnm9mdbwDOYhbXmHCVQ0LBnMAX0mGhVA4jsScJd4kwfcieWrV2mz4_x53ibA7WwuT8EPOEG1qGWa_RwOVQqAUrH43H7BI3hoJlWAmwi0wJVhrd5mNrcSn288Kr2NGukxT8pHiU5-vtbx4pP5T4DW4uglbjdZob__zfTVgv4KZdz-fHFizJbBvKiDBzguYdIPXMFGHZfQ237XRiC0SUeip8vL2_mrypFHiP5_2_UI-78Ni8ebi-dYpGCg7XeCRwUsZJRBhJpadiDdFSN6UhVRFlMfEEDXlQU3FKXOlHnpRuxCIecil0xMqUqqnAr0ApG2RyD2ymw-lAahCiUXkQCkJpFCrfJ8INldKrnwXns8FMeMEyjs0u-sks2sBhSMwwWHA6lx3m3Bo_SlWMTuYiOoClyGNnQXWmpKQwvHHiIYeXoSGz4GT-WJsM7oOkmRxMxwnBxqRYgEssuDAq--XzSbfXuzJX-38RPoa1TqOZtO7a9wdQ1iiL5nmbKpQmo6k8hFX-ojU9Oiqm7CenUu7X |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Another+look+at+distance%E2%80%90weighted+discrimination&rft.jtitle=Journal+of+the+Royal+Statistical+Society.+Series+B%2C+Statistical+methodology&rft.au=Wang%2C+Boxiang&rft.au=Zou%2C+Hui&rft.date=2018-01-01&rft.issn=1369-7412&rft.volume=80&rft.issue=1+p.177-198&rft.spage=177&rft.epage=198&rft_id=info:doi/10.1111%2Frssb.12244&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1369-7412&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1369-7412&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1369-7412&client=summon |