Adversarial classification via distributional robustness with Wasserstein ambiguity
We study a model for adversarial classification based on distributionally robust chance constraints. We show that under Wasserstein ambiguity, the model aims to minimize the conditional value-at-risk of the distance to misclassification, and we explore links to adversarial classification models prop...
Uloženo v:
| Vydáno v: | Mathematical programming Ročník 198; číslo 2; s. 1411 - 1447 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Berlin/Heidelberg
Springer Berlin Heidelberg
01.04.2023
Springer |
| Témata: | |
| ISSN: | 0025-5610, 1436-4646 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | We study a model for adversarial classification based on distributionally robust chance constraints. We show that under Wasserstein ambiguity, the model aims to minimize the conditional value-at-risk of the distance to misclassification, and we explore links to adversarial classification models proposed earlier and to maximum-margin classifiers. We also provide a reformulation of the distributionally robust model for linear classification, and show it is equivalent to minimizing a regularized ramp loss objective. Numerical experiments show that, despite the nonconvexity of this formulation, standard descent methods appear to converge to the global minimizer for this problem. Inspired by this observation, we show that, for a certain class of distributions, the only stationary point of the regularized ramp loss minimization problem is the global minimizer. |
|---|---|
| AbstractList | We study a model for adversarial classification based on distributionally robust chance constraints. We show that under Wasserstein ambiguity, the model aims to minimize the conditional value-at-risk of the distance to misclassification, and we explore links to adversarial classification models proposed earlier and to maximum-margin classifiers. We also provide a reformulation of the distributionally robust model for linear classification, and show it is equivalent to minimizing a regularized ramp loss objective. Numerical experiments show that, despite the nonconvexity of this formulation, standard descent methods appear to converge to the global minimizer for this problem. Inspired by this observation, we show that, for a certain class of distributions, the only stationary point of the regularized ramp loss minimization problem is the global minimizer. |
| Audience | Academic |
| Author | Wright, Stephen J. Ho-Nguyen, Nam |
| Author_xml | – sequence: 1 givenname: Nam orcidid: 0000-0003-4464-7730 surname: Ho-Nguyen fullname: Ho-Nguyen, Nam email: nam.ho-nguyen@sydney.edu.au organization: Discipline of Business Analytics, The University of Sydney – sequence: 2 givenname: Stephen J. surname: Wright fullname: Wright, Stephen J. organization: Computer Sciences Department, University of Wisconsin |
| BookMark | eNp90M1KAzEQwPEgCrbVF_C0L7B1kt1NtsdS_IKCBxWPYTab1CnbXUnSSt_etPXkoeQQGPLLwH_MLvuht4zdcZhyAHUfOHBQOQiRA1czmcsLNuJlIfNSlvKSjQBElVeSwzUbh7AGAF7U9Yi9zdud9QE9YZeZDkMgRwYjDX22I8xaCtFTsz0M0gs_NNsQextC9kPxK_tMIPFoqc9w09BqS3F_w64cdsHe_t0T9vH48L54zpevTy-L-TI3hSpjXlqByFthURStUw26xqBSBThVGayEcaJ2xgCYsrWNUyXy2klpJApjHPJiwqanf1fYWU29G6JHk05rN2RSIEdpPlcln9WygCoBcQLGDyF46_S3pw36veagDx31qaNOHfWxo5YJ1f-QoXgMlLZRd54WJxrSnn5lvV4PW586hnPqF_5djVs |
| CitedBy_id | crossref_primary_10_1016_j_compind_2024_104213 crossref_primary_10_1137_22M1538946 crossref_primary_10_1007_s10107_024_02163_3 crossref_primary_10_1007_s40305_025_00580_5 |
| Cites_doi | 10.1198/016214507000000617 10.1287/opre.2015.1374 10.1016/j.ejor.2017.03.051 10.1007/BF01589116 10.1287/ijoo.2018.0001 10.1287/opre.2018.1764 10.1137/100818327 10.1111/j.1467-9965.2007.00311.x 10.1007/s10107-017-1172-1 10.1109/TSP.2019.2937282 10.1007/s10107-019-01445-5 10.1287/opre.1100.0854 10.1287/opre.13.3.444 10.1109/TIT.2021.3100107 10.1080/10556789208805504 10.1007/s10589-016-9847-8 10.1287/moor.2018.0936 10.1093/imanum/dry009 10.1198/016214503000000639 10.1080/10556780802712889 10.1007/978-3-030-02185-6 10.1109/CVPR.2019.00929 10.1287/educ.1073.0032 10.1109/SP.2017.49 10.1287/educ.2019.0198 10.1002/9781119432036 10.7551/mitpress/8996.003.0016 10.1145/3128572.3140444 10.1109/CVPR.2016.282 10.1145/1143844.1143870 10.1007/s10994-017-5663-3 10.1137/1.9781611971309 |
| ContentType | Journal Article |
| Copyright | Crown 2022 COPYRIGHT 2023 Springer |
| Copyright_xml | – notice: Crown 2022 – notice: COPYRIGHT 2023 Springer |
| DBID | C6C AAYXX CITATION |
| DOI | 10.1007/s10107-022-01796-6 |
| DatabaseName | SpringerOpen Free (Free internet resource, activated by CARLI) CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Mathematics |
| EISSN | 1436-4646 |
| EndPage | 1447 |
| ExternalDocumentID | A741986305 10_1007_s10107_022_01796_6 |
| GrantInformation_xml | – fundername: National Science Foundation grantid: 1740707; 2023239 funderid: http://dx.doi.org/10.13039/100000001 – fundername: National Science Foundation grantid: 1628384; 1634597 funderid: http://dx.doi.org/10.13039/100000001 – fundername: Argonne National Laboratory grantid: Subcontract 8F- 30039 funderid: http://dx.doi.org/10.13039/100006224 – fundername: Defense Advanced Research Projects Agency grantid: N660011824020 funderid: http://dx.doi.org/10.13039/100000185 |
| GroupedDBID | --K --Z -52 -5D -5G -BR -EM -Y2 -~C -~X .4S .86 .DC .VR 06D 0R~ 0VY 199 1B1 1N0 1OL 1SB 203 28- 29M 2J2 2JN 2JY 2KG 2KM 2LR 2P1 2VQ 2~H 30V 3V. 4.4 406 408 409 40D 40E 5GY 5QI 5VS 67Z 6NX 6TJ 78A 7WY 88I 8AO 8FE 8FG 8FL 8TC 8UJ 8VB 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDBF ABDZT ABECU ABFTV ABHLI ABHQN ABJCF ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACGOD ACHSB ACHXU ACIWK ACKNC ACMDZ ACMLO ACNCT ACOKC ACOMO ACPIV ACUHS ACZOJ ADHHG ADHIR ADIMF ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMOZ AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFEXP AFFNX AFGCZ AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHQJS AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ AKVCP ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN AZQEC B-. B0M BA0 BAPOH BBWZM BDATZ BENPR BEZIV BGLVJ BGNMA BPHCQ BSONS C6C CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 DWQXO EAD EAP EBA EBLON EBR EBS EBU ECS EDO EIOEI EJD EMI EMK EPL ESBYG EST ESX FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRNLG FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNUQQ GNWQR GQ6 GQ7 GQ8 GROUPED_ABI_INFORM_COMPLETE GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ H~9 I-F I09 IAO IHE IJ- IKXTQ ITM IWAJR IXC IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ K1G K60 K6V K6~ K7- KDC KOV KOW L6V LAS LLZTM M0C M0N M2P M4Y M7S MA- N2Q N9A NB0 NDZJH NPVJJ NQ- NQJWS NU0 O9- O93 O9G O9I O9J OAM P19 P2P P62 P9R PF0 PQBIZ PQBZA PQQKQ PROAC PT4 PT5 PTHSS Q2X QOK QOS QWB R4E R89 R9I RHV RIG RNI RNS ROL RPX RPZ RSV RZK S16 S1Z S26 S27 S28 S3B SAP SCLPG SDD SDH SDM SHX SISQX SJYHP SMT SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TH9 TN5 TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WH7 WK8 XPP YLTOR Z45 Z5O Z7R Z7S Z7X Z7Y Z7Z Z81 Z83 Z86 Z88 Z8M Z8N Z8R Z8T Z8W Z92 ZL0 ZMTXR ZWQNP ~02 ~8M ~EX AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG ADXHL AEZWR AFDZB AFFHD AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP AMVHM ATHPR AYFIA CITATION PHGZM PHGZT PQGLB |
| ID | FETCH-LOGICAL-c374t-4e2aa1d2ea23df7bafbca7730f75ca52cf28fcc00c4debf74a18f66c6a2ccfa13 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 9 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000779032900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0025-5610 |
| IngestDate | Sat Nov 29 10:28:58 EST 2025 Sat Nov 29 03:34:03 EST 2025 Tue Nov 18 22:03:02 EST 2025 Fri Feb 21 02:43:37 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Keywords | 90C30 Wasserstein ambiguity Ramp loss 68T09 90C17 Adversarial cassification 90C26 Nonconvex Distributional robustness Margin |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c374t-4e2aa1d2ea23df7bafbca7730f75ca52cf28fcc00c4debf74a18f66c6a2ccfa13 |
| ORCID | 0000-0003-4464-7730 |
| OpenAccessLink | https://link.springer.com/10.1007/s10107-022-01796-6 |
| PageCount | 37 |
| ParticipantIDs | gale_infotracacademiconefile_A741986305 crossref_primary_10_1007_s10107_022_01796_6 crossref_citationtrail_10_1007_s10107_022_01796_6 springer_journals_10_1007_s10107_022_01796_6 |
| PublicationCentury | 2000 |
| PublicationDate | 20230400 2023-04-00 20230401 |
| PublicationDateYYYYMMDD | 2023-04-01 |
| PublicationDate_xml | – month: 4 year: 2023 text: 20230400 |
| PublicationDecade | 2020 |
| PublicationPlace | Berlin/Heidelberg |
| PublicationPlace_xml | – name: Berlin/Heidelberg |
| PublicationSubtitle | A Publication of the Mathematical Optimization Society |
| PublicationTitle | Mathematical programming |
| PublicationTitleAbbrev | Math. Program |
| PublicationYear | 2023 |
| Publisher | Springer Berlin Heidelberg Springer |
| Publisher_xml | – name: Springer Berlin Heidelberg – name: Springer |
| References | Xie (CR52) 2021; 186 CR37 CR36 CR33 CR31 CR30 Brooks (CR10) 2011; 59 Shafieezadeh-Abadeh, Kuhn, Mohajerin Esfahani (CR44) 2019; 20 Beck, Teboulle (CR1) 2012; 22 Bertsimas, Copenhaver (CR6) 2018; 270 Ben-Tal, Hazan, Koren, Mannor (CR4) 2015; 63 Ho-Nguyen, Kılınç-Karzan (CR27) 2018; 66 Mohajerin Esfahani, Kuhn (CR35) 2018; 171 Mangasarian (CR34) 1965; 13 CR49 CR48 CR47 CR46 Belotti, Bonami, Fischetti, Lodi, Monaci, Nogales-Gómez, Salvagnin (CR2) 2016; 65 CR43 CR42 CR40 Blanchet, Murthy (CR8) 2019; 44 Bollapragada, Byrd, Nocedal (CR9) 2019; 39 Ben-Tal, Teboulle (CR3) 2007; 17 Nocedal, Wright (CR39) 2006 Wu, Liu (CR51) 2007; 102 CR19 CR17 CR15 CR14 CR13 CR57 CR12 CR56 CR11 CR55 Chi, Lu, Chen (CR18) 2019; 67 CR54 Chen, Paschalidis (CR16) 2018; 19 CR50 Liu, Nocedal (CR32) 1989; 45 Mutapcic, Boyd (CR38) 2009; 24 Xu, Caramanis, Mannor (CR53) 2009; 10 CR29 Pydi, Jog (CR41) 2021; 67 CR28 CR26 CR25 Bennett, Mangasarian (CR5) 1992; 1 CR24 CR23 Bertsimas, Dunn, Pawlowski, Zhuo (CR7) 2019; 1 CR22 CR21 CR20 Shen, Tseng, Zhang, Wong (CR45) 2003; 98 D Bertsimas (1796_CR6) 2018; 270 P Mohajerin Esfahani (1796_CR35) 2018; 171 OL Mangasarian (1796_CR34) 1965; 13 JP Brooks (1796_CR10) 2011; 59 1796_CR49 S Shafieezadeh-Abadeh (1796_CR44) 2019; 20 1796_CR46 1796_CR48 P Belotti (1796_CR2) 2016; 65 KP Bennett (1796_CR5) 1992; 1 1796_CR47 1796_CR42 1796_CR43 D Bertsimas (1796_CR7) 2019; 1 N Ho-Nguyen (1796_CR27) 2018; 66 1796_CR40 DC Liu (1796_CR32) 1989; 45 W Xie (1796_CR52) 2021; 186 R Chen (1796_CR16) 2018; 19 J Blanchet (1796_CR8) 2019; 44 1796_CR37 1796_CR36 1796_CR31 1796_CR30 1796_CR33 A Mutapcic (1796_CR38) 2009; 24 Y Wu (1796_CR51) 2007; 102 1796_CR28 X Shen (1796_CR45) 2003; 98 A Ben-Tal (1796_CR4) 2015; 63 Y Chi (1796_CR18) 2019; 67 1796_CR29 1796_CR24 1796_CR23 A Ben-Tal (1796_CR3) 2007; 17 1796_CR26 1796_CR25 1796_CR20 1796_CR22 1796_CR21 A Beck (1796_CR1) 2012; 22 MS Pydi (1796_CR41) 2021; 67 H Xu (1796_CR53) 2009; 10 1796_CR17 1796_CR19 1796_CR13 1796_CR57 1796_CR12 1796_CR56 1796_CR15 J Nocedal (1796_CR39) 2006 1796_CR14 1796_CR11 1796_CR55 1796_CR54 1796_CR50 R Bollapragada (1796_CR9) 2019; 39 |
| References_xml | – ident: CR22 – ident: CR49 – volume: 102 start-page: 974 issue: 479 year: 2007 end-page: 983 ident: CR51 article-title: Robust truncated hinge loss support vector machines publication-title: J. Am. Stat. Assoc. doi: 10.1198/016214507000000617 – volume: 63 start-page: 628 issue: 3 year: 2015 end-page: 638 ident: CR4 article-title: Oracle-based robust optimization via online learning publication-title: Oper. Res. doi: 10.1287/opre.2015.1374 – volume: 270 start-page: 931 issue: 3 year: 2018 end-page: 942 ident: CR6 article-title: Characterization of the equivalence of robustification and regularization in linear and matrix regression publication-title: Eur. J. Oper. Res. doi: 10.1016/j.ejor.2017.03.051 – ident: CR12 – year: 2006 ident: CR39 publication-title: Numerical optimization – volume: 45 start-page: 503 issue: 1 year: 1989 end-page: 528 ident: CR32 article-title: On the limited memory BFGS method for large scale optimization publication-title: Math. Program. doi: 10.1007/BF01589116 – volume: 10 start-page: 1485 issue: 51 year: 2009 end-page: 1510 ident: CR53 article-title: Robustness and regularization of support vector machines publication-title: J. Mach. Learn. Res. – volume: 1 start-page: 2 issue: 1 year: 2019 end-page: 34 ident: CR7 article-title: Robust classification publication-title: INFORMS J. Optim. doi: 10.1287/ijoo.2018.0001 – volume: 66 start-page: 1670 issue: 6 year: 2018 end-page: 1692 ident: CR27 article-title: Online first-order framework for robust convex optimization publication-title: Oper. Res. doi: 10.1287/opre.2018.1764 – volume: 22 start-page: 557 issue: 2 year: 2012 end-page: 580 ident: CR1 article-title: Smoothing and first order methods: a unified framework publication-title: SIAM J. Optim. doi: 10.1137/100818327 – ident: CR29 – ident: CR54 – volume: 17 start-page: 449 issue: 3 year: 2007 end-page: 476 ident: CR3 article-title: An old-new concept of convex risk measures: the optimized certainty equivalent publication-title: Math. Finance doi: 10.1111/j.1467-9965.2007.00311.x – volume: 20 start-page: 1 issue: 103 year: 2019 end-page: 68 ident: CR44 article-title: Regularization via mass transportation publication-title: J. Mach. Learn. Res. – ident: CR25 – ident: CR42 – ident: CR21 – ident: CR46 – ident: CR19 – volume: 171 start-page: 115 issue: 1 year: 2018 end-page: 166 ident: CR35 article-title: Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations publication-title: Math. Program. doi: 10.1007/s10107-017-1172-1 – ident: CR15 – ident: CR50 – volume: 67 start-page: 5239 issue: 20 year: 2019 end-page: 5269 ident: CR18 article-title: Nonconvex optimization meets low-rank matrix factorization: an overview publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2019.2937282 – volume: 186 start-page: 115 issue: 1 year: 2021 end-page: 155 ident: CR52 article-title: On distributionally robust chance constrained programs with Wasserstein distance publication-title: Math. Program. doi: 10.1007/s10107-019-01445-5 – volume: 59 start-page: 467 issue: 2 year: 2011 end-page: 479 ident: CR10 article-title: Support vector machines with the ramp loss and the hard margin loss publication-title: Oper. Res. doi: 10.1287/opre.1100.0854 – ident: CR11 – ident: CR57 – ident: CR36 – ident: CR26 – volume: 13 start-page: 444 issue: 3 year: 1965 end-page: 452 ident: CR34 article-title: Linear and nonlinear separation of patterns by linear programming publication-title: Oper. Res. doi: 10.1287/opre.13.3.444 – ident: CR43 – ident: CR47 – ident: CR14 – volume: 67 start-page: 6031 issue: 9 year: 2021 end-page: 6052 ident: CR41 article-title: Adversarial risk via optimal transport and optimal couplings publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2021.3100107 – ident: CR37 – volume: 1 start-page: 23 issue: 1 year: 1992 end-page: 34 ident: CR5 article-title: Robust linear programming discrimination of two linearly inseparable sets publication-title: Optim. Methods Softw. doi: 10.1080/10556789208805504 – ident: CR30 – ident: CR33 – volume: 65 start-page: 545 issue: 3 year: 2016 end-page: 566 ident: CR2 article-title: On handling indicator constraints in mixed integer programming publication-title: Comput. Optim. Appl. doi: 10.1007/s10589-016-9847-8 – ident: CR56 – ident: CR40 – ident: CR23 – ident: CR48 – volume: 44 start-page: 565 issue: 2 year: 2019 end-page: 600 ident: CR8 article-title: Quantifying distributional model risk via optimal transport publication-title: Math. Oper. Res. doi: 10.1287/moor.2018.0936 – volume: 39 start-page: 545 issue: 2 year: 2019 end-page: 578 ident: CR9 article-title: Exact and inexact subsampled Newton methods for optimization publication-title: IMA J. Numer. Anal. doi: 10.1093/imanum/dry009 – ident: CR17 – ident: CR31 – ident: CR13 – volume: 98 start-page: 724 issue: 463 year: 2003 end-page: 734 ident: CR45 article-title: On -learning publication-title: J. Am. Stat. Assoc. doi: 10.1198/016214503000000639 – volume: 19 start-page: 1 issue: 13 year: 2018 end-page: 48 ident: CR16 article-title: A robust learning approach for regression models based on distributionally robust optimization publication-title: J. Mach. Learn. Res. – volume: 24 start-page: 381 issue: 3 year: 2009 end-page: 406 ident: CR38 article-title: Cutting-set methods for robust convex optimization with pessimizing oracles publication-title: Optim. Methods Softw. doi: 10.1080/10556780802712889 – ident: CR55 – ident: CR28 – ident: CR24 – ident: CR20 – volume: 186 start-page: 115 issue: 1 year: 2021 ident: 1796_CR52 publication-title: Math. Program. doi: 10.1007/s10107-019-01445-5 – volume: 102 start-page: 974 issue: 479 year: 2007 ident: 1796_CR51 publication-title: J. Am. Stat. Assoc. doi: 10.1198/016214507000000617 – ident: 1796_CR24 doi: 10.1007/978-3-030-02185-6 – volume: 17 start-page: 449 issue: 3 year: 2007 ident: 1796_CR3 publication-title: Math. Finance doi: 10.1111/j.1467-9965.2007.00311.x – ident: 1796_CR46 – ident: 1796_CR33 – ident: 1796_CR37 doi: 10.1109/CVPR.2019.00929 – ident: 1796_CR14 – ident: 1796_CR56 – volume: 63 start-page: 628 issue: 3 year: 2015 ident: 1796_CR4 publication-title: Oper. Res. doi: 10.1287/opre.2015.1374 – ident: 1796_CR42 doi: 10.1287/educ.1073.0032 – ident: 1796_CR47 – ident: 1796_CR22 – volume: 65 start-page: 545 issue: 3 year: 2016 ident: 1796_CR2 publication-title: Comput. Optim. Appl. doi: 10.1007/s10589-016-9847-8 – volume: 19 start-page: 1 issue: 13 year: 2018 ident: 1796_CR16 publication-title: J. Mach. Learn. Res. – ident: 1796_CR12 doi: 10.1109/SP.2017.49 – volume: 171 start-page: 115 issue: 1 year: 2018 ident: 1796_CR35 publication-title: Math. Program. doi: 10.1007/s10107-017-1172-1 – volume: 67 start-page: 6031 issue: 9 year: 2021 ident: 1796_CR41 publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2021.3100107 – volume: 20 start-page: 1 issue: 103 year: 2019 ident: 1796_CR44 publication-title: J. Mach. Learn. Res. – volume: 67 start-page: 5239 issue: 20 year: 2019 ident: 1796_CR18 publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2019.2937282 – ident: 1796_CR26 – ident: 1796_CR43 – volume: 1 start-page: 2 issue: 1 year: 2019 ident: 1796_CR7 publication-title: INFORMS J. Optim. doi: 10.1287/ijoo.2018.0001 – ident: 1796_CR11 – volume: 13 start-page: 444 issue: 3 year: 1965 ident: 1796_CR34 publication-title: Oper. Res. doi: 10.1287/opre.13.3.444 – ident: 1796_CR29 doi: 10.1287/educ.2019.0198 – ident: 1796_CR57 – ident: 1796_CR15 – ident: 1796_CR48 – volume: 1 start-page: 23 issue: 1 year: 1992 ident: 1796_CR5 publication-title: Optim. Methods Softw. doi: 10.1080/10556789208805504 – volume: 24 start-page: 381 issue: 3 year: 2009 ident: 1796_CR38 publication-title: Optim. Methods Softw. doi: 10.1080/10556780802712889 – ident: 1796_CR40 doi: 10.1002/9781119432036 – volume-title: Numerical optimization year: 2006 ident: 1796_CR39 – volume: 22 start-page: 557 issue: 2 year: 2012 ident: 1796_CR1 publication-title: SIAM J. Optim. doi: 10.1137/100818327 – ident: 1796_CR25 – volume: 66 start-page: 1670 issue: 6 year: 2018 ident: 1796_CR27 publication-title: Oper. Res. doi: 10.1287/opre.2018.1764 – volume: 39 start-page: 545 issue: 2 year: 2019 ident: 1796_CR9 publication-title: IMA J. Numer. Anal. doi: 10.1093/imanum/dry009 – volume: 270 start-page: 931 issue: 3 year: 2018 ident: 1796_CR6 publication-title: Eur. J. Oper. Res. doi: 10.1016/j.ejor.2017.03.051 – ident: 1796_CR54 doi: 10.7551/mitpress/8996.003.0016 – volume: 10 start-page: 1485 issue: 51 year: 2009 ident: 1796_CR53 publication-title: J. Mach. Learn. Res. – ident: 1796_CR13 doi: 10.1145/3128572.3140444 – ident: 1796_CR31 – ident: 1796_CR36 doi: 10.1109/CVPR.2016.282 – ident: 1796_CR21 doi: 10.1145/1143844.1143870 – ident: 1796_CR50 – ident: 1796_CR49 – volume: 59 start-page: 467 issue: 2 year: 2011 ident: 1796_CR10 publication-title: Oper. Res. doi: 10.1287/opre.1100.0854 – volume: 44 start-page: 565 issue: 2 year: 2019 ident: 1796_CR8 publication-title: Math. Oper. Res. doi: 10.1287/moor.2018.0936 – ident: 1796_CR20 – ident: 1796_CR28 – ident: 1796_CR23 doi: 10.1007/s10994-017-5663-3 – ident: 1796_CR17 – ident: 1796_CR30 – ident: 1796_CR55 – ident: 1796_CR19 doi: 10.1137/1.9781611971309 – volume: 45 start-page: 503 issue: 1 year: 1989 ident: 1796_CR32 publication-title: Math. Program. doi: 10.1007/BF01589116 – volume: 98 start-page: 724 issue: 463 year: 2003 ident: 1796_CR45 publication-title: J. Am. Stat. Assoc. doi: 10.1198/016214503000000639 |
| SSID | ssj0001388 |
| Score | 2.4730403 |
| Snippet | We study a model for adversarial classification based on distributionally robust chance constraints. We show that under Wasserstein ambiguity, the model aims... |
| SourceID | gale crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1411 |
| SubjectTerms | Calculus of Variations and Optimal Control; Optimization Combinatorics Full Length Paper Mathematical and Computational Physics Mathematical Methods in Physics Mathematics Mathematics and Statistics Mathematics of Computing Numerical Analysis Theoretical |
| Title | Adversarial classification via distributional robustness with Wasserstein ambiguity |
| URI | https://link.springer.com/article/10.1007/s10107-022-01796-6 |
| Volume | 198 |
| WOSCitedRecordID | wos000779032900001&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: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1436-4646 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001388 issn: 0025-5610 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEA5aPejBt1hf7EHwoIFmd5tNj0UsHrSI9dFbmMxmpaCtdLf9_Wb2UVuQgh4XsiHMTGYmycz3MXah3EnHiEbA4yZYHmJDcQUi5qFx8c_GSRQV6Pr3Uber-v3WY9kUllbV7tWTZO6p55rdBF2r-VRKELUkl6tszYU7RYQNT73Xmf8VgVIVUStlB2WrzO9zLISjyikvPonmkaaz_b817rCtMrP02oUp7LIVO9xjm3N4g-7rYQbSmu6zXk7GnAKZoIeURVPZUK4pbzoALyZM3ZIOy40Yj8wkzcgzenR5671B3qlJbJkefJrB-8Ql9AfspXP7fHPHS44FjkEUZjy0Pjjd-Bb8wGnGQGIQIrftk6iJ0PQx8VWC2GhgGFuTRCEIlUiJEnzEBERwyGrD0dAeMQ9tgM5dSGOMpP5XBdYlVzEIK2SslKgzUYlaYwlATjwYH_oHOpnEp534dC4-LevsavbPVwG_sXT0JWlQ0950MyOULQZufYRypdsufWop6VxcnV1XCtTlpk2XTHz8t-EnbINY6YsCn1NWy8YTe8bWcZoN0vF5bq3f7fTlXw |
| linkProvider | Springer Nature |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS8MwED_8AvXBb3F-9kHwQQtL26XZo4hDcQ7RqXsLl2sqA91k3fz7zXXtVJCBPhbSEO4ud5fk7vcDOFbupGNENfSTGlo_oqryFYrEj4yLfzZJ43iMrt-MWy3V6dTviqawrKx2L58kc0_9rdlN8LVawKUEcV36chbmIxexGDH__uFp4n9FqFRJ1MrZQdEq8_scP8JR6ZR_Ponmkaax-r81rsFKkVl652NTWIcZ29uA5W94g-7rdgLSmm3CQ07GnCGboEecRXPZUK4p76OLXsKYugUdlhsx6JtRNmTP6PHlrfeMeacms2V6-Ga6LyOX0G_BY-OyfXHlFxwLPoVxNPQjG6DTTWAxCJ1mDKaGMHbbPo1rhLWA0kClRNUqRYk1aRyhUKmUJDEgSlGE2zDX6_fsDnhkQ3LuQhpjJPe_KrQuuUpQWCETpUQFRClqTQUAOfNgvOov6GQWn3bi07n4tKzA6eSf9zH8xtTRJ6xBzXvTzUxYtBi49THKlT536VNdSefiKnBWKlAXmzabMvHu34YfweJV-7apm9etmz1YYob6cbHPPswNByN7AAv0Mexmg8Pccj8Btt7oQw |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LTxsxEB6VtELtASgPNTzKHpB6gFXi3Y3XOSIgalWIkGiBmzWetVEkCCi7ye-vZx9pkBAS4riS17Jm7PHYnu_7AA6UP-kY0Y3DrIc2TKirQoUiCxPj9z-buTSt2PXP0-FQ3d72LxdQ_GW1e_MkWWEamKVpXHSeMtdZAL4JvmKLuKwg7ctQLsHHhAvp-bx-dT2PxSJWqhFt5Uyhhs283MezrakJ0M-fR8tdZ7D6_vGuwUqdcQbH1RT5Ch_seB2-LPAQ-q-LOXlrvgFXpUhzjjw1A-LsmsuJSg8GsxEGGXPt1jJZvsXk0UzzgiNmwJe6wQ2WCE5W0QzwwYzupj7R34S_g7M_Jz_DWnshpDhNijCxEXqfRRaj2HvMoDOEqQ8HLu0R9iJykXJE3S4lmTUuTVAoJyVJjIgcingLWuPHsf0GAdmYfBiRxhjJuFiF1iddGQorZKaUaINozK6pJiZnfYx7_Z9Smc2nvfl0aT4t23A4_-epouV4tfUP9qbmNet7JqyhB358zH6lj31a1VfSh742HDXO1PVizl_pePttzfdh-fJ0oM9_DX_vwGcWrq9qgHahVUymdg8-0awY5ZPv5ST-B77B8Sc |
| 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=Adversarial+classification+via+distributional+robustness+with+Wasserstein+ambiguity&rft.jtitle=Mathematical+programming&rft.au=Ho-Nguyen%2C+Nam&rft.au=Wright%2C+Stephen+J.&rft.date=2023-04-01&rft.pub=Springer+Berlin+Heidelberg&rft.issn=0025-5610&rft.eissn=1436-4646&rft.volume=198&rft.issue=2&rft.spage=1411&rft.epage=1447&rft_id=info:doi/10.1007%2Fs10107-022-01796-6&rft.externalDocID=10_1007_s10107_022_01796_6 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0025-5610&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0025-5610&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0025-5610&client=summon |