Dataset Shift in Machine Learning
Dataset shift is a common problem in predictive modeling that occurs when the joint distribution of inputs and outputs differs between training and test stages. Covariate shift, a particular case of dataset shift, occurs when only the input distribution changes. Dataset shift is present in most prac...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | E-Book Buch |
| Sprache: | Englisch |
| Veröffentlicht: |
Cambridge, Mass
MIT Press
2008
The MIT Press |
| Ausgabe: | 1 |
| Schriftenreihe: | Neural Information Processing series |
| Schlagworte: | |
| ISBN: | 0262170051, 9780262170055 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Dataset shift is a common problem in predictive modeling that occurs when the joint distribution of inputs and outputs differs between training and test stages. Covariate shift, a particular case of dataset shift, occurs when only the input distribution changes. Dataset shift is present in most practical applications, for reasons ranging from the bias introduced by experimental design to the irreproducibility of the testing conditions at training time. (An example is -email spam filtering, which may fail to recognize spam that differs in form from the spam the automatic filter has been built on.) Despite this, and despite the attention given to the apparently similar problems of semi-supervised learning and active learning, dataset shift has received relatively little attention in the machine learning community until recently. This volume offers an overview of current efforts to deal with dataset and covariate shift. The chapters offer a mathematical and philosophical introduction to the problem, place dataset shift in relationship to transfer learning, transduction, local learning, active learning, and semi-supervised learning, provide theoretical views of dataset and covariate shift (including decision theoretic and Bayesian perspectives), and present algorithms for covariate shift. Contributors [cut for catalog if necessary]Shai Ben-David, Steffen Bickel, Karsten Borgwardt, Michael Brückner, David Corfield, Amir Globerson, Arthur Gretton, Lars Kai Hansen, Matthias Hein, Jiayuan Huang, Choon Hui Teo, Takafumi Kanamori, Klaus-Robert Müller, Sam Roweis, Neil Rubens, Tobias Scheffer, Marcel Schmittfull, Bernhard Schölkopf Hidetoshi Shimodaira, Alex Smola, Amos Storkey, Masashi Sugiyama |
|---|---|
| AbstractList | Dataset shift is a common problem in predictive modeling that occurs when
the joint distribution of inputs and outputs differs between training and test
stages. Covariate shift, a particular case of dataset shift, occurs when only the
input distribution changes. Dataset shift is present in most practical applications,
for reasons ranging from the bias introduced by experimental design to the
irreproducibility of the testing conditions at training time. (An example is -email
spam filtering, which may fail to recognize spam that differs in form from the spam
the automatic filter has been built on.) Despite this, and despite the attention
given to the apparently similar problems of semi-supervised learning and active
learning, dataset shift has received relatively little attention in the machine
learning community until recently. This volume offers an overview of current efforts
to deal with dataset and covariate shift. The chapters offer a mathematical and
philosophical introduction to the problem, place dataset shift in relationship to
transfer learning, transduction, local learning, active learning, and
semi-supervised learning, provide theoretical views of dataset and covariate shift
(including decision theoretic and Bayesian perspectives), and present algorithms for
covariate shift. Contributors [cut for catalog if necessary]Shai Ben-David, Steffen
Bickel, Karsten Borgwardt, Michael Brückner, David Corfield, Amir Globerson, Arthur
Gretton, Lars Kai Hansen, Matthias Hein, Jiayuan Huang, Choon Hui Teo, Takafumi
Kanamori, Klaus-Robert Müller, Sam Roweis, Neil Rubens, Tobias Scheffer, Marcel
Schmittfull, Bernhard Schölkopf Hidetoshi Shimodaira, Alex Smola, Amos Storkey,
Masashi Sugiyama This work is an overview of recent efforts in the machine learning community to deal with dataset and covariate shift, which occurs when test and training inputs and outputs have different distributions. An overview of recent efforts in the machine learning community to deal with dataset and covariate shift, which occurs when test and training inputs and outputs have different distributions. An overview of recent efforts in the machine learning community to deal with dataset and covariate shift, which occurs when test and training inputs and outputs have different distributions. Dataset shift is a common problem in predictive modeling that occurs when the joint distribution of inputs and outputs differs between training and test stages. Covariate shift, a particular case of dataset shift, occurs when only the input distribution changes. Dataset shift is present in most practical applications, for reasons ranging from the bias introduced by experimental design to the irreproducibility of the testing conditions at training time. (An example is -email spam filtering, which may fail to recognize spam that differs in form from the spam the automatic filter has been built on.) Despite this, and despite the attention given to the apparently similar problems of semi-supervised learning and active learning, dataset shift has received relatively little attention in the machine learning community until recently. This volume offers an overview of current efforts to deal with dataset and covariate shift. The chapters offer a mathematical and philosophical introduction to the problem, place dataset shift in relationship to transfer learning, transduction, local learning, active learning, and semi-supervised learning, provide theoretical views of dataset and covariate shift (including decision theoretic and Bayesian perspectives), and present algorithms for covariate shift. Contributors Shai Ben-David, Steffen Bickel, Karsten Borgwardt, Michael Brückner, David Corfield, Amir Globerson, Arthur Gretton, Lars Kai Hansen, Matthias Hein, Jiayuan Huang, Choon Hui Teo, Takafumi Kanamori, Klaus-Robert Müller, Sam Roweis, Neil Rubens, Tobias Scheffer, Marcel Schmittfull, Bernhard Schölkopf Hidetoshi Shimodaira, Alex Smola, Amos Storkey, Masashi Sugiyama Dataset shift is a common problem in predictive modeling that occurs when the joint distribution of inputs and outputs differs between training and test stages. Covariate shift, a particular case of dataset shift, occurs when only the input distribution changes. Dataset shift is present in most practical applications, for reasons ranging from the bias introduced by experimental design to the irreproducibility of the testing conditions at training time. (An example is -email spam filtering, which may fail to recognize spam that differs in form from the spam the automatic filter has been built on.) Despite this, and despite the attention given to the apparently similar problems of semi-supervised learning and active learning, dataset shift has received relatively little attention in the machine learning community until recently. This volume offers an overview of current efforts to deal with dataset and covariate shift. The chapters offer a mathematical and philosophical introduction to the problem, place dataset shift in relationship to transfer learning, transduction, local learning, active learning, and semi-supervised learning, provide theoretical views of dataset and covariate shift (including decision theoretic and Bayesian perspectives), and present algorithms for covariate shift. Contributors [cut for catalog if necessary]Shai Ben-David, Steffen Bickel, Karsten Borgwardt, Michael Brückner, David Corfield, Amir Globerson, Arthur Gretton, Lars Kai Hansen, Matthias Hein, Jiayuan Huang, Choon Hui Teo, Takafumi Kanamori, Klaus-Robert Müller, Sam Roweis, Neil Rubens, Tobias Scheffer, Marcel Schmittfull, Bernhard Schölkopf Hidetoshi Shimodaira, Alex Smola, Amos Storkey, Masashi Sugiyama |
| Author | Quiñonero-Candela, Joaquin |
| Author_xml | – sequence: 1 fullname: Quinonero-Candela, Joaquin – sequence: 2 fullname: Sugiyama, Masashi – sequence: 3 fullname: Schwaighofer, Anton – sequence: 4 fullname: Lawrence, Neil D |
| BackLink | https://cir.nii.ac.jp/crid/1130000796189520896$$DView record in CiNii |
| BookMark | eNqNkctOAzEMRYN4CFr6AeyKhIRYFOykeS2hPKUiFiC2UdJxaaDMQDPA75PpFCR2LBwvfHyt3NthG2VVEmOHCMdaSjx5jfXbglI6sdoAVxw1gJTHAJgLcI31VgOeaRDrrPNL4SbrcIA8BWGHW2xHIFiUVg-3WS-lZ2gEhEQOO2z_3Nc-Ud2_n8Vp3Y9l_9ZPZrGk_pj8oozl0y7bnPp5ot6qd9nj5cXD6Howvru6GZ2OB94gcDsQgUNAr0Mo9DBr2yA8BGWNkcVUKVVwEkMCqxVprqbGFJk3NAlUoCl0EF121Ar79EJfaVbN6-Q-5xSq6iW5n99aLoX8J7t0JrOHLfu2qN4_KNVuiU2orBd-7i7ORkIIY3WjetCSZYxuEpsXUTR2aavQWMnBWJUx02I5I9deRHBNau4nNfcnNZf9dkvTu2yvXY1EtNpVXGm0VnwDMkmKQg |
| ContentType | eBook Book |
| Copyright | 2009 Massachusetts Institute of Technology |
| Copyright_xml | – notice: 2009 Massachusetts Institute of Technology |
| DBID | RYH |
| DEWEY | 006.3/1 |
| DOI | 10.7551/mitpress/9780262170055.001.0001 |
| DatabaseName | CiNii Complete |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISBN | 9780262255103 0262255103 9780262292535 026229253X |
| Edition | 1 |
| Editor | Sugiyama, Masashi Quiñonero-Candela, Joaquin Schwaighofer, Anton Lawrence, Neil D |
| Editor_xml | – sequence: 1 givenname: Joaquin surname: Quiñonero-Candela fullname: Quiñonero-Candela, Joaquin – sequence: 2 givenname: Masashi surname: Sugiyama fullname: Sugiyama, Masashi – sequence: 3 givenname: Anton surname: Schwaighofer fullname: Schwaighofer, Anton – sequence: 4 givenname: Neil D surname: Lawrence fullname: Lawrence, Neil D |
| ExternalDocumentID | 9780262292535 9780262255103 EBC3338975 BA91110311 10_7551_mitpress_9780262170055_001_0001 6267199 |
| GroupedDBID | -D2 05S 089 20A 28 2K9 38. 6IK 92K A4I A4J AAALR AABBV AAJDW ABARN ABFDN ABFEK ABHES ABIAV ABQPQ ABWNX ACLGV ADVEM AERYV AILDO AIXPE AJFER AJYPA AKHYG ALMA_UNASSIGNED_HOLDINGS AOFLF APVFW AQ. AZZ BBABE BEFXN BFFAM BGNUA BKEBE BPEOZ CDLGT CWTWH CZZ C~9 D2 DHNOV DUGUG DYIFQ E2F EBBCW EBSCA ECNEQ GEOUK HF4 IVK JJU MICIX MIJRL MYL O7H OCL PLCCB PQEST PQQKQ PQUKI TI5 UE6 VQ VX W2P XI1 -VQ -VX AAFKH AAIPT AAJRE AAKGN AANYM AAOBU AAZGR ABIWA ABOMZ ADBND ADJTR ADYUQ AECLD AEGYG AEHEP AFQEX AGGIE AIGZA AMYDA ATDNW BSWCA CVDBJ ECOWB L7C NRCWT ABAZT ABMRC ABQNV ABRSK ACHUA AHWGJ RYH BJTYN |
| ID | FETCH-LOGICAL-a81029-3b20b1a7bbd741209b3a0b69885df666d2e34e0976e726f88d20b8ecbed18d7b3 |
| ISBN | 0262170051 9780262170055 |
| ISICitedReferencesCount | 295 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=(TOP02)005963631&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Fri Sep 12 03:45:39 EDT 2025 Fri Nov 08 06:15:09 EST 2024 Wed Dec 10 10:35:06 EST 2025 Fri Jun 27 01:20:46 EDT 2025 Tue Jun 18 19:46:18 EDT 2024 Tue Jul 13 16:44:46 EDT 2021 |
| IsPeerReviewed | false |
| IsScholarly | false |
| LCCN | 2008020394 |
| LCCallNum_Ident | Q325.5 |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-a81029-3b20b1a7bbd741209b3a0b69885df666d2e34e0976e726f88d20b8ecbed18d7b3 |
| Notes | Includes bibliographical references (p. 207-218) and index |
| OCLC | 310915974 |
| PQID | EBC3338975 |
| PageCount | 248 |
| ParticipantIDs | askewsholts_vlebooks_9780262292535 askewsholts_vlebooks_9780262255103 proquest_ebookcentral_EBC3338975 nii_cinii_1130000796189520896 mit_books_10_7551_mitpress_9780262170055_001_0001 ieee_books_6267199 |
| ProviderPackageCode | BPEOZ BGNUA ECNEQ 6IK DYIFQ OCL BKEBE -D2 BEFXN BFFAM MIJRL |
| PublicationCentury | 2000 |
| PublicationDate | 2008 20081212 c2009 2008-12-12 |
| PublicationDateYYYYMMDD | 2008-01-01 2008-12-12 2009-01-01 |
| PublicationDate_xml | – year: 2008 text: 2008 |
| PublicationDecade | 2000 |
| PublicationPlace | Cambridge, Mass |
| PublicationPlace_xml | – name: Cambridge, Mass – name: Cambridge |
| PublicationSeriesTitle | Neural Information Processing series |
| PublicationYear | 2008 2009 |
| Publisher | MIT Press The MIT Press |
| Publisher_xml | – name: MIT Press – name: The MIT Press |
| SSID | ssj0000135120 |
| Score | 2.4007847 |
| Snippet | Dataset shift is a common problem in predictive modeling that occurs when the joint distribution of inputs and outputs differs between training and test... An overview of recent efforts in the machine learning community to deal with dataset and covariate shift, which occurs when test and training inputs and... Dataset shift is a common problem in predictive modeling that occurs when the joint distribution of inputs and outputs differs between training and test... This work is an overview of recent efforts in the machine learning community to deal with dataset and covariate shift, which occurs when test and training... |
| SourceID | askewsholts proquest nii mit ieee |
| SourceType | Aggregation Database Publisher |
| SubjectTerms | Computer Science Computing and Processing Machine learning Machine Learning & Neural Networks Mathematical models |
| TableOfContents | Intro -- Contents -- Series Foreword -- Preface -- I - Introduction to Dataset Shift -- 1 - When Training and Test Sets Are Di erent: Characterizing Learning Transfer -- 2 - Projection and Projectability -- II - Theoretical Views on Dataset and Covariate Shift -- 3 - Binary Classi cation under Sample Selection Bias -- 4 - On Bayesian Transduction: Implications for the Covariate Shift Problem -- 5 - On the Training/Test Distributions Gap: A Data Representation Learning Framework -- III - Algorithms for Covariate Shift -- 6 - Geometry of Covariate Shift with Applications to Active Learning -- 7 - A Conditional Expectation Approach to Model Selection and Active Learning under Covariate Shift -- 8 - Covariate Shift by Kernel Mean Matching -- 9 - Discriminative Learning under Covariate Shift with a Single Optimization Problem -- 10 - An Adversarial View of Covariate Shift and a Minimax Approach -- IV - Discussion -- 11 - Author Comments -- References -- Notation and Symbols -- Contributors -- Index |
| Title | Dataset Shift in Machine Learning |
| URI | https://ieeexplore.ieee.org/servlet/opac?bknumber=6267199 http://dx.doi.org/10.7551/mitpress/9780262170055.001.0001 https://cir.nii.ac.jp/crid/1130000796189520896 https://ebookcentral.proquest.com/lib/[SITE_ID]/detail.action?docID=3338975 https://www.vlebooks.com/vleweb/product/openreader?id=none&isbn=9780262255103&uid=none https://www.vlebooks.com/vleweb/product/openreader?id=none&isbn=9780262292535&uid=none |
| WOSCitedRecordID | wos(TOP02)005963631&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 | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwEB7BLkL0AuWhplAUEBKnqLETx_a1ZQEJKBxK1VsUJ3YV0aaoG6r-fGYcJ8tCJR4SFyuxM1nvTDyP-MsMwIs6xwGdywTNjUxyx1VihMoSLmvHKueE8hvtR-_lwYE6PtafQk28pS8nILtOXV3pr_9V1NiHwqZPZ_9C3NNNsQOPUejYotix_ckjnk4Hib-qejRJlIO5dT7x_wcPlLRjDtWTtQhfEVqCreJBel5Qj61hMobwD-MnXI6UE-86ZShxBCd71vYeUjtAIYiEUvIJepXEKHsjW1mCCZ-HkQFRlyNtuUZJODi_aX0T5jwXWT6D-ZvFx8_vppdbKdX94-lteBnmsTveaff6OWzARrX8gmodVX6_DJVu0NwjGbZd2_5iKr39P7wHc0sfhWzCDdvdh7tjKYw4aMYH8CwwP_bMj9suDsyPR-Y_hKPXi8P9t0moPpFUihEoKDM8NaySxjTodvFUm6xKTaGVEo3DqK_hNsttiv6clbxwSjV4vbK1sQ1TjTTZI5h1553dgjivC9R1Dp0_U-SNsFrYxnBTMFxAjgsVwfMf_n55eep3yie2DzL-3UWai0xEsEmsK4chjFYl0zoChowMfX8o2wh2kO1l3VLLaNMTvUkqD6QFT5UuIohHgZR-IgFMXC729rMM3WAptv_hZx_DndUSeAKz_uKb3YFb9WXfLi-ehufsO8mASVg |
| linkProvider | ProQuest Ebooks |
| 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%3Abook&rft.genre=book&rft.title=Dataset+Shift+in+Machine+Learning&rft.date=2008-12-12&rft.pub=The+MIT+Press&rft.isbn=9780262255103&rft_id=info:doi/10.7551%2Fmitpress%2F9780262170055.001.0001&rft.externalDocID=10_7551_mitpress_9780262170055_001_0001 |
| thumbnail_m | http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fvle.dmmserver.com%2Fmedia%2F640%2F97802622%2F9780262255103.jpg http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fvle.dmmserver.com%2Fmedia%2F640%2F97802622%2F9780262292535.jpg |