Disagreement-Based Active Learning in Online Settings

We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen examples. The objective is to minimize the number of queries wh...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on signal processing Ročník 70; s. 1947 - 1958
Hlavní autoři: Huang, Boshuang, Salgia, Sudeep, Zhao, Qing
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Active learning
Algorithms
Classification
Complexity
Complexity theory
Distance learning
Errors
label complexity
Learning theory
Lower bounds
Machine learning
online learning
Optimization
Particle separators
Picture archiving and communication systems
Prediction algorithms
Queries
Real-time systems
regret
Signal processing algorithms
statistical learning theory
Tradeoffs
ISSN:1053-587X, 1941-0476
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen examples. The objective is to minimize the number of queries while constraining the number of prediction errors over a horizon of length <inline-formula><tex-math notation="LaTeX">T</tex-math></inline-formula>. We develop a disagreement-based online learning algorithm for a general hypothesis space and under the Tsybakov noise and establish its label complexity under a constraint of bounded regret in terms of classification errors. We further establish a matching (up to a poly-logarithmic factor) lower bound, demonstrating the order optimality of the proposed algorithm. We address the tradeoff between label complexity and regret and show that the algorithm can be modified to operate at a different point on the tradeoff curve.
AbstractList We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen examples. The objective is to minimize the number of queries while constraining the number of prediction errors over a horizon of length [Formula Omitted]. We develop a disagreement-based online learning algorithm for a general hypothesis space and under the Tsybakov noise and establish its label complexity under a constraint of bounded regret in terms of classification errors. We further establish a matching (up to a poly-logarithmic factor) lower bound, demonstrating the order optimality of the proposed algorithm. We address the tradeoff between label complexity and regret and show that the algorithm can be modified to operate at a different point on the tradeoff curve.
We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen examples. The objective is to minimize the number of queries while constraining the number of prediction errors over a horizon of length <inline-formula><tex-math notation="LaTeX">T</tex-math></inline-formula>. We develop a disagreement-based online learning algorithm for a general hypothesis space and under the Tsybakov noise and establish its label complexity under a constraint of bounded regret in terms of classification errors. We further establish a matching (up to a poly-logarithmic factor) lower bound, demonstrating the order optimality of the proposed algorithm. We address the tradeoff between label complexity and regret and show that the algorithm can be modified to operate at a different point on the tradeoff curve.
Author Huang, Boshuang
Salgia, Sudeep
Zhao, Qing
Author_xml – sequence: 1
  givenname: Boshuang
  orcidid: 0000-0003-0597-6179
  surname: Huang
  fullname: Huang, Boshuang
  email: bh467@cornell.edu
  organization: School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA
– sequence: 2
  givenname: Sudeep
  orcidid: 0000-0003-1361-4565
  surname: Salgia
  fullname: Salgia, Sudeep
  email: ss3827@cornell.edu
  organization: School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA
– sequence: 3
  givenname: Qing
  orcidid: 0000-0002-9590-4285
  surname: Zhao
  fullname: Zhao, Qing
  email: qz16@cornell.edu
  organization: School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA
BookMark eNp9kE1rAjEQhkOxULW9F3pZ6HltvndztPYTBAta6C3E7KxENGuTWOi_b0TpoYeeZhjeZ4Z5BqjnOw8IXRM8IgSru8X8bUQxpSNGhGJ1fYb6RHFSYl7JXu6xYKWoq48LNIhxjTHhXMk-Eg8umlUA2IJP5b2J0BRjm9wXFFMwwTu_KpwvZn7jPBRzSClP4iU6b80mwtWpDtH70-Ni8lJOZ8-vk_G0tFSRVPLaMIuJtEyISoBqq5Yul5QpYmXDLJPYKmUoN7SRDRFLIyvSEGU4tMZSw9kQ3R737kL3uYeY9LrbB59Pairzm1xhXucUPqZs6GIM0OpdcFsTvjXB-iBHZzn6IEef5GRE_kGsSya5zqdg3OY_8OYIOgD4vaMqJhjD7AfAMnI0
CODEN ITPRED
CitedBy_id crossref_primary_10_1109_TSP_2024_3450270
crossref_primary_10_1109_TSP_2022_3159388
crossref_primary_10_1016_j_apenergy_2024_124832
crossref_primary_10_1109_TSP_2024_3451412
crossref_primary_10_1007_s10994_023_06454_2
crossref_primary_10_1016_j_est_2025_117016
Cites_doi 10.1109/TIT.2008.920189
10.1109/TSP.2017.2731323
10.1109/ICASSP.2018.8461409
10.1145/1553374.1553381
10.1145/1273496.1273541
10.1007/11503415_17
10.1214/009053606000000786
10.1007/978-3-540-72927-3_5
10.1109/TSP.2014.2304431
10.1016/j.neucom.2019.06.064
10.1214/10-AOS843
10.1007/978-3-540-28650-9_8
10.1109/TIT.2011.2162269
10.1007/978-3-540-45167-9_28
10.1109/TIT.2014.2304455
10.1007/978-3-319-21852-6_3
10.1145/1143844.1143853
10.1214/aos/1079120131
10.1145/2591796.2591839
10.1214/009053606000001019
10.1214/19-EJS1635
10.1109/TSP.2022.3159388
10.1109/TSP.2010.2042491
10.1007/BF00993277
10.2200/S00429ED1V01Y201207AIM018
10.1609/aaai.v31i1.10907
10.1561/2200000037
10.1016/j.tcs.2010.12.054
10.1023/A:1007330508534
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TSP.2022.3159388
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1941-0476
EndPage 1958
ExternalDocumentID 10_1109_TSP_2022_3159388
9735330
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  grantid: CCF-1815559
  funderid: 10.13039/501100008982
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
53G
5GY
5VS
6IK
85S
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACIWK
ACKIV
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AJQPL
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
E.L
EBS
EJD
F5P
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c291t-48a3c016c35575e9f7f2bb2391c6d3c360c99a24a2d6d15ba671d19a4efac2a43
IEDL.DBID RIE
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000790809400002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1053-587X
IngestDate Mon Jun 30 10:13:08 EDT 2025
Sat Nov 29 04:10:55 EST 2025
Tue Nov 18 22:11:34 EST 2025
Wed Aug 27 02:40:12 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c291t-48a3c016c35575e9f7f2bb2391c6d3c360c99a24a2d6d15ba671d19a4efac2a43
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-9590-4285
0000-0003-1361-4565
0000-0003-0597-6179
PQID 2659349048
PQPubID 85478
PageCount 12
ParticipantIDs crossref_primary_10_1109_TSP_2022_3159388
ieee_primary_9735330
proquest_journals_2659349048
crossref_citationtrail_10_1109_TSP_2022_3159388
PublicationCentury 2000
PublicationDate 20220000
2022-00-00
20220101
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – year: 2022
  text: 20220000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on signal processing
PublicationTitleAbbrev TSP
PublicationYear 2022
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref35
ref34
Dasgupta (ref12) 2008
ref15
ref14
ref36
Beygelzimer (ref11) 2011
ref30
ref2
ref1
ref17
ref39
Awasthi (ref18) 2015
ref38
Zhang (ref22) 2014; 1
Awasthi (ref19) 2016; 49
Cortes (ref21) 2019
Cavallanti (ref31) 2009
Hanneke (ref37) 2015; 16
Koltchinskii (ref7) 2010; 11
ref24
ref23
ref26
ref25
ref41
ref44
Cortes (ref33) 2019
ref43
Beygelzimer (ref10) 2010
ref28
Balcan (ref16) 2013
ref27
Yang (ref32) 2011
ref29
ref8
ref9
ref4
ref3
ref5
Zhang (ref20) 2018; 75
ref40
Freund (ref42) 1997; 28
Hanneke (ref6) 2009
References_xml – ident: ref36
  doi: 10.1109/TIT.2008.920189
– ident: ref26
  doi: 10.1109/TSP.2017.2731323
– ident: ref28
  doi: 10.1109/ICASSP.2018.8461409
– ident: ref9
  doi: 10.1145/1553374.1553381
– start-page: 249
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2009
  ident: ref31
  article-title: Linear classification and selective sampling under low noise conditions
– ident: ref5
  doi: 10.1145/1273496.1273541
– ident: ref14
  doi: 10.1007/11503415_17
– ident: ref38
  doi: 10.1214/009053606000000786
– volume: 49
  start-page: 152
  issue: 6
  year: 2016
  ident: ref19
  article-title: Learning and 1-bit compressed sensing under asymmetric noise
  publication-title: J. Mach. Learn. Res.
– ident: ref15
  doi: 10.1007/978-3-540-72927-3_5
– ident: ref29
  doi: 10.1109/TSP.2014.2304431
– volume: 16
  start-page: 3487
  issue: 1
  year: 2015
  ident: ref37
  article-title: Minimax analysis of active learning
  publication-title: J. Mach. Learn. Res.
– ident: ref44
  doi: 10.1016/j.neucom.2019.06.064
– ident: ref8
  doi: 10.1214/10-AOS843
– ident: ref39
  doi: 10.1007/978-3-540-28650-9_8
– volume-title: Proc. 22nd Conf. Learn. Theory (COLT)
  year: 2009
  ident: ref6
  article-title: Adaptive rates of convergence in active learning
– ident: ref24
  doi: 10.1109/TIT.2011.2162269
– ident: ref30
  doi: 10.1007/978-3-540-45167-9_28
– volume: 11
  start-page: 2457
  issue: 9
  year: 2010
  ident: ref7
  article-title: Rademacher complexities and bounding the excess risk in active learning
  publication-title: J. Mach. Learn. Res.
– volume: 1
  start-page: 442
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2014
  ident: ref22
  article-title: Beyond disagreement-based agnostic active learning
– ident: ref25
  doi: 10.1109/TIT.2014.2304455
– volume-title: Proc. Workshop On-line Trading Exploration Exploitation
  year: 2011
  ident: ref11
  article-title: Efficient active learning
– ident: ref40
  doi: 10.1007/978-3-319-21852-6_3
– ident: ref4
  doi: 10.1145/1143844.1143853
– ident: ref34
  doi: 10.1214/aos/1079120131
– start-page: 288
  volume-title: Proc. Conf. Learn. Theory
  year: 2013
  ident: ref16
  article-title: Active and passive learning of linear separators under log-concave distributions
– ident: ref17
  doi: 10.1145/2591796.2591839
– ident: ref35
  doi: 10.1214/009053606000001019
– ident: ref13
  doi: 10.1214/19-EJS1635
– start-page: 167
  volume-title: Conf. Learn. Theory
  year: 2015
  ident: ref18
  article-title: Efficient learning of linear separators under bounded noise
– start-page: 2801
  volume-title: Proc. 22nd Int. Conf. Artif. Intell. Statist.
  year: 2019
  ident: ref21
  article-title: Region-based active learning
– start-page: 2468
  volume-title: Proc. 36th Int. Conf. Mach. Learn.
  year: 2019
  ident: ref33
  article-title: Active learning with disagreement graphs
– ident: ref41
  doi: 10.1109/TSP.2022.3159388
– ident: ref27
  doi: 10.1109/TSP.2010.2042491
– volume: 75
  start-page: 1
  volume-title: Proc. Mach. Learn. Res.
  year: 2018
  ident: ref20
  article-title: Efficient active learning of sparse halfspaces
– ident: ref1
  doi: 10.1007/BF00993277
– start-page: 2079
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2011
  ident: ref32
  article-title: Active learning with a drifting distribution
– ident: ref23
  doi: 10.2200/S00429ED1V01Y201207AIM018
– ident: ref43
  doi: 10.1609/aaai.v31i1.10907
– ident: ref3
  doi: 10.1561/2200000037
– ident: ref2
  doi: 10.1016/j.tcs.2010.12.054
– volume: 28
  start-page: 133
  issue: 2-3
  year: 1997
  ident: ref42
  article-title: Selective sampling using the query by committee algorithm
  publication-title: Mach. Learn.
  doi: 10.1023/A:1007330508534
– start-page: 353
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2008
  ident: ref12
  article-title: A general agnostic active learning algorithm
– start-page: 199
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2010
  ident: ref10
  article-title: Agnostic active learning without constraints
SSID ssj0014496
Score 2.4421282
Snippet We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1947
SubjectTerms Active learning
Algorithms
Classification
Complexity
Complexity theory
Distance learning
Errors
label complexity
Learning theory
Lower bounds
Machine learning
online learning
Optimization
Particle separators
Picture archiving and communication systems
Prediction algorithms
Queries
Real-time systems
regret
Signal processing algorithms
statistical learning theory
Tradeoffs
Title Disagreement-Based Active Learning in Online Settings
URI https://ieeexplore.ieee.org/document/9735330
https://www.proquest.com/docview/2659349048
Volume 70
WOSCitedRecordID wos000790809400002&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1941-0476
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014496
  issn: 1053-587X
  databaseCode: RIE
  dateStart: 19910101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH9sw4Me_JridEoPXgTj2iRtmuP8GJ7GYBN2K2mSykA6WTf_fl_TrgqK4K2HvEf5pX0feS_vB3Cd0TT2hTYkDqwhXIURkdRYwkyE8UdqFQo6sgkxHsfzuZy04La5C2Otdc1n9q58dLV8s9Sb8qhsIAUrmyHb0BYiqu5qNRUDzh0XF4YLjISxmG9Lkr4czKYTTAQpxfw0lMxxrHy5IMep8sMQO-8yOvjfex3Cfh1FesNq24-gZfNj2Ps2W7AL4eOiUJhMu-M_co_OynhDZ9y8eqbqq7fIvWrUqDe1rv-5OIGX0dPs4ZnUHAlEUxmsCY8V0xi2aYwbRGhlJhD9lDIZ6MgwzSJfS6koV9REBsFXkQhMIBW3mdJUcXYKnXyZ2zPwjEYtXIeZDlOOyhTXnCkE1gRlDZ73YLCFLdH1APGSx-ItcYmELxMEOimBTmqge3DTSLxXwzP-WNstgW3W1Zj2oL_dmaT-u4qERijCJRqf89-lLmC31F0dlfShs15t7CXs6I_1olhduQ_nExVWv3o
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmqgHX2hEUffgxcQK23YfPeKDYERCAibcNt22GBIDhgV_v9PugiYaE2976HQ3X7vz6EznA7gc0TRuREqT2DeacBmERFBtCNMh-h-pkSjoyCaibjceDkWvBNeruzDGGFd8Zm7so8vl66la2KOyuoiYLYZcg_WAY9yT39Za5Qw4d2xc6DAwEsTRcJmUbIj6oN_DUJBSjFADwRzLypcRcqwqP1Sxsy-t3f992R7sFH6k18wXfh9KZnIA29-6C1YguB9nEsNpdwBIbtFcaa_p1JtXdFV99cYTL2826vWNq4DODuGl9TC4a5OCJYEoKvw54bFkCh03hZ5DFBgxihD_lDLhq1AzxcKGEkJSLqkONcIvw8jXvpDcjKSikrMjKE-mE3MMnlY4C1fBSAUpx8kkV5xJBFb7NgvPq1BfwpaoooW4ZbJ4S1wo0RAJAp1YoJMC6CpcrSTe8_YZf4ytWGBX4wpMq1BbrkxS_F9ZQkMU4QLVz8nvUhew2R48d5LOY_fpFLbse_KDkxqU57OFOYMN9TEfZ7Nzt4k-ATpJwsE
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=Disagreement-Based+Active+Learning+in+Online+Settings&rft.jtitle=IEEE+transactions+on+signal+processing&rft.au=Huang%2C+Boshuang&rft.au=Salgia%2C+Sudeep&rft.au=Zhao%2C+Qing&rft.date=2022&rft.pub=IEEE&rft.issn=1053-587X&rft.volume=70&rft.spage=1947&rft.epage=1958&rft_id=info:doi/10.1109%2FTSP.2022.3159388&rft.externalDocID=9735330
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-587X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-587X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-587X&client=summon