Distributionally robust learning:
This monograph provides insight into a technique that has gained a lot of recent interest in developing robust supervised learning solutions that are founded in sound mathematical principles. It will be enlightening for researchers, practitioners and students in the optimization of machine learning...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Elektronisch E-Book |
| Sprache: | English |
| Veröffentlicht: |
Boston ; Delft
Now Publishers
2020
|
| Schriftenreihe: | Foundations and trends in optimization
Vol. 4, no. 1-2 |
| Schlagworte: | |
| Online-Zugang: | TUM01 |
| Zusammenfassung: | This monograph provides insight into a technique that has gained a lot of recent interest in developing robust supervised learning solutions that are founded in sound mathematical principles. It will be enlightening for researchers, practitioners and students in the optimization of machine learning systems Intro -- Introduction -- Robust Optimization -- Distributionally Robust Optimization -- Outline -- Notational Conventions -- Abbreviations -- The Wasserstein Metric -- Basics -- A Distance Metric -- The Dual Problem -- Some Special Cases -- The Transport Cost Function -- Robustness of the Wasserstein Ambiguity Set -- Setting the Radius of the Wasserstein Ball -- Solving the Wasserstein DRO Problem -- Dual Method -- The Extreme Distribution -- A Discrete Empirical Nominal Distribution -- Finite Sample Performance -- Asymptotic Consistency -- Distributionally Robust Linear Regression -- The Problem and Related Work -- The Wasserstein DRO Formulation for Linear Regression -- Performance Guarantees for the DRO Estimator -- Experiments on the Performance of Wasserstein DRO -- An Application of Wasserstein DRO to Outlier Detection -- Summary -- Distributionally Robust Grouped Variable Selection -- The Problem and Related Work -- The Groupwise Wasserstein Grouped LASSO -- Performance Guarantees to the DRO Groupwise Estimator -- Numerical Experiments -- Summary -- Distributionally Robust Multi-Output Learning -- The Problem and Related Work -- Distributionally Robust Multi-Output Learning Models -- The Out-of-Sample Performance Guarantees -- Numerical Experiments -- Summary -- Optimal Decision Making via Regression Informed K-NN -- The Problem and Related Work -- Robust Nonlinear Predictive Model -- Prescriptive Policy Development -- Developing Optimal Prescriptions for Patients -- Summary -- Advanced Topics in Distributionally Robust Learning -- Distributionally Robust Learning with Unlabeled Data -- Distributionally Robust Reinforcement Learning -- Discussion and Conclusions -- Acknowledgments -- References |
| Beschreibung: | Description based on publisher supplied metadata and other sources |
| Beschreibung: | 1 online resource (252 pages) |
| ISBN: | 9781680837735 |
Internformat
MARC
| LEADER | 00000nmm a22000001cb4500 | ||
|---|---|---|---|
| 001 | BV047886990 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | cr|uuu---uuuuu | ||
| 008 | 220317s2020 |||| o||u| ||||||eng d | ||
| 020 | |a 9781680837735 |9 978-1-68083-773-5 | ||
| 024 | 7 | |a 10.1561/2400000026 |2 doi | |
| 035 | |a (OCoLC)1304478592 | ||
| 035 | |a (DE-599)KEP060922389 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-91 | ||
| 100 | 1 | |a Chen, Ruidi |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Distributionally robust learning |c Ruidi Chen, Ioannis Ch. Paschalidis |
| 264 | 1 | |a Boston ; Delft |b Now Publishers |c 2020 | |
| 300 | |a 1 online resource (252 pages) | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b c |2 rdamedia | ||
| 338 | |b cr |2 rdacarrier | ||
| 490 | 1 | |a Foundations and trends in optimization |v Vol. 4, no. 1-2 | |
| 500 | |a Description based on publisher supplied metadata and other sources | ||
| 520 | 3 | |a This monograph provides insight into a technique that has gained a lot of recent interest in developing robust supervised learning solutions that are founded in sound mathematical principles. It will be enlightening for researchers, practitioners and students in the optimization of machine learning systems | |
| 520 | 3 | |a Intro -- Introduction -- Robust Optimization -- Distributionally Robust Optimization -- Outline -- Notational Conventions -- Abbreviations -- The Wasserstein Metric -- Basics -- A Distance Metric -- The Dual Problem -- Some Special Cases -- The Transport Cost Function -- Robustness of the Wasserstein Ambiguity Set -- Setting the Radius of the Wasserstein Ball -- Solving the Wasserstein DRO Problem -- Dual Method -- The Extreme Distribution -- A Discrete Empirical Nominal Distribution -- Finite Sample Performance -- Asymptotic Consistency -- Distributionally Robust Linear Regression -- The Problem and Related Work -- The Wasserstein DRO Formulation for Linear Regression -- Performance Guarantees for the DRO Estimator -- Experiments on the Performance of Wasserstein DRO -- An Application of Wasserstein DRO to Outlier Detection -- Summary -- Distributionally Robust Grouped Variable Selection -- The Problem and Related Work -- The Groupwise Wasserstein Grouped LASSO -- Performance Guarantees to the DRO Groupwise Estimator -- Numerical Experiments -- Summary -- Distributionally Robust Multi-Output Learning -- The Problem and Related Work -- Distributionally Robust Multi-Output Learning Models -- The Out-of-Sample Performance Guarantees -- Numerical Experiments -- Summary -- Optimal Decision Making via Regression Informed K-NN -- The Problem and Related Work -- Robust Nonlinear Predictive Model -- Prescriptive Policy Development -- Developing Optimal Prescriptions for Patients -- Summary -- Advanced Topics in Distributionally Robust Learning -- Distributionally Robust Learning with Unlabeled Data -- Distributionally Robust Reinforcement Learning -- Discussion and Conclusions -- Acknowledgments -- References | |
| 653 | 0 | |a Electronic books | |
| 700 | 1 | |a Paschalidis, Ioannis Ch. |e Verfasser |4 aut | |
| 776 | 0 | 8 | |i Erscheint auch als |n Druck-Ausgabe |z 978-1-68083-772-8 |
| 830 | 0 | |a Foundations and trends in optimization |v Vol. 4, no. 1-2 |w (DE-604)BV047879910 |9 4,1/2 | |
| 912 | |a ebook | ||
| 999 | |a oai:aleph.bib-bvb.de:BVB01-033269184 | ||
| 966 | e | |u https://www.nowpublishers.com/article/Download/OPT-026 |l TUM01 |p ebook |x Verlag |3 Volltext | |
Datensatz im Suchindex
| _version_ | 1804183489211269120 |
|---|---|
| adam_txt | |
| any_adam_object | |
| any_adam_object_boolean | |
| author | Chen, Ruidi Paschalidis, Ioannis Ch |
| author_facet | Chen, Ruidi Paschalidis, Ioannis Ch |
| author_role | aut aut |
| author_sort | Chen, Ruidi |
| author_variant | r c rc i c p ic icp |
| building | Verbundindex |
| bvnumber | BV047886990 |
| collection | ebook |
| ctrlnum | (OCoLC)1304478592 (DE-599)KEP060922389 |
| format | Electronic eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03396nmm a22003851cb4500</leader><controlfield tag="001">BV047886990</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">cr|uuu---uuuuu</controlfield><controlfield tag="008">220317s2020 |||| o||u| ||||||eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781680837735</subfield><subfield code="9">978-1-68083-773-5</subfield></datafield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1561/2400000026</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1304478592</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)KEP060922389</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Chen, Ruidi</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Distributionally robust learning</subfield><subfield code="c">Ruidi Chen, Ioannis Ch. Paschalidis</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Boston ; Delft</subfield><subfield code="b">Now Publishers</subfield><subfield code="c">2020</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 online resource (252 pages)</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Foundations and trends in optimization</subfield><subfield code="v">Vol. 4, no. 1-2</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Description based on publisher supplied metadata and other sources</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">This monograph provides insight into a technique that has gained a lot of recent interest in developing robust supervised learning solutions that are founded in sound mathematical principles. It will be enlightening for researchers, practitioners and students in the optimization of machine learning systems</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Intro -- Introduction -- Robust Optimization -- Distributionally Robust Optimization -- Outline -- Notational Conventions -- Abbreviations -- The Wasserstein Metric -- Basics -- A Distance Metric -- The Dual Problem -- Some Special Cases -- The Transport Cost Function -- Robustness of the Wasserstein Ambiguity Set -- Setting the Radius of the Wasserstein Ball -- Solving the Wasserstein DRO Problem -- Dual Method -- The Extreme Distribution -- A Discrete Empirical Nominal Distribution -- Finite Sample Performance -- Asymptotic Consistency -- Distributionally Robust Linear Regression -- The Problem and Related Work -- The Wasserstein DRO Formulation for Linear Regression -- Performance Guarantees for the DRO Estimator -- Experiments on the Performance of Wasserstein DRO -- An Application of Wasserstein DRO to Outlier Detection -- Summary -- Distributionally Robust Grouped Variable Selection -- The Problem and Related Work -- The Groupwise Wasserstein Grouped LASSO -- Performance Guarantees to the DRO Groupwise Estimator -- Numerical Experiments -- Summary -- Distributionally Robust Multi-Output Learning -- The Problem and Related Work -- Distributionally Robust Multi-Output Learning Models -- The Out-of-Sample Performance Guarantees -- Numerical Experiments -- Summary -- Optimal Decision Making via Regression Informed K-NN -- The Problem and Related Work -- Robust Nonlinear Predictive Model -- Prescriptive Policy Development -- Developing Optimal Prescriptions for Patients -- Summary -- Advanced Topics in Distributionally Robust Learning -- Distributionally Robust Learning with Unlabeled Data -- Distributionally Robust Reinforcement Learning -- Discussion and Conclusions -- Acknowledgments -- References</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electronic books</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Paschalidis, Ioannis Ch.</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Druck-Ausgabe</subfield><subfield code="z">978-1-68083-772-8</subfield></datafield><datafield tag="830" ind1=" " ind2="0"><subfield code="a">Foundations and trends in optimization</subfield><subfield code="v">Vol. 4, no. 1-2</subfield><subfield code="w">(DE-604)BV047879910</subfield><subfield code="9">4,1/2</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ebook</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-033269184</subfield></datafield><datafield tag="966" ind1="e" ind2=" "><subfield code="u">https://www.nowpublishers.com/article/Download/OPT-026</subfield><subfield code="l">TUM01</subfield><subfield code="p">ebook</subfield><subfield code="x">Verlag</subfield><subfield code="3">Volltext</subfield></datafield></record></collection> |
| id | DE-604.BV047886990 |
| illustrated | Not Illustrated |
| index_date | 2024-07-03T19:24:47Z |
| indexdate | 2024-07-10T09:24:15Z |
| institution | BVB |
| isbn | 9781680837735 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-033269184 |
| oclc_num | 1304478592 |
| open_access_boolean | |
| owner | DE-91 DE-BY-TUM |
| owner_facet | DE-91 DE-BY-TUM |
| physical | 1 online resource (252 pages) |
| psigel | ebook |
| publishDate | 2020 |
| publishDateSearch | 2020 |
| publishDateSort | 2020 |
| publisher | Now Publishers |
| record_format | marc |
| series | Foundations and trends in optimization |
| series2 | Foundations and trends in optimization |
| spelling | Chen, Ruidi Verfasser aut Distributionally robust learning Ruidi Chen, Ioannis Ch. Paschalidis Boston ; Delft Now Publishers 2020 1 online resource (252 pages) txt rdacontent c rdamedia cr rdacarrier Foundations and trends in optimization Vol. 4, no. 1-2 Description based on publisher supplied metadata and other sources This monograph provides insight into a technique that has gained a lot of recent interest in developing robust supervised learning solutions that are founded in sound mathematical principles. It will be enlightening for researchers, practitioners and students in the optimization of machine learning systems Intro -- Introduction -- Robust Optimization -- Distributionally Robust Optimization -- Outline -- Notational Conventions -- Abbreviations -- The Wasserstein Metric -- Basics -- A Distance Metric -- The Dual Problem -- Some Special Cases -- The Transport Cost Function -- Robustness of the Wasserstein Ambiguity Set -- Setting the Radius of the Wasserstein Ball -- Solving the Wasserstein DRO Problem -- Dual Method -- The Extreme Distribution -- A Discrete Empirical Nominal Distribution -- Finite Sample Performance -- Asymptotic Consistency -- Distributionally Robust Linear Regression -- The Problem and Related Work -- The Wasserstein DRO Formulation for Linear Regression -- Performance Guarantees for the DRO Estimator -- Experiments on the Performance of Wasserstein DRO -- An Application of Wasserstein DRO to Outlier Detection -- Summary -- Distributionally Robust Grouped Variable Selection -- The Problem and Related Work -- The Groupwise Wasserstein Grouped LASSO -- Performance Guarantees to the DRO Groupwise Estimator -- Numerical Experiments -- Summary -- Distributionally Robust Multi-Output Learning -- The Problem and Related Work -- Distributionally Robust Multi-Output Learning Models -- The Out-of-Sample Performance Guarantees -- Numerical Experiments -- Summary -- Optimal Decision Making via Regression Informed K-NN -- The Problem and Related Work -- Robust Nonlinear Predictive Model -- Prescriptive Policy Development -- Developing Optimal Prescriptions for Patients -- Summary -- Advanced Topics in Distributionally Robust Learning -- Distributionally Robust Learning with Unlabeled Data -- Distributionally Robust Reinforcement Learning -- Discussion and Conclusions -- Acknowledgments -- References Electronic books Paschalidis, Ioannis Ch. Verfasser aut Erscheint auch als Druck-Ausgabe 978-1-68083-772-8 Foundations and trends in optimization Vol. 4, no. 1-2 (DE-604)BV047879910 4,1/2 |
| spellingShingle | Chen, Ruidi Paschalidis, Ioannis Ch Distributionally robust learning Foundations and trends in optimization |
| title | Distributionally robust learning |
| title_auth | Distributionally robust learning |
| title_exact_search | Distributionally robust learning |
| title_exact_search_txtP | Distributionally robust learning |
| title_full | Distributionally robust learning Ruidi Chen, Ioannis Ch. Paschalidis |
| title_fullStr | Distributionally robust learning Ruidi Chen, Ioannis Ch. Paschalidis |
| title_full_unstemmed | Distributionally robust learning Ruidi Chen, Ioannis Ch. Paschalidis |
| title_short | Distributionally robust learning |
| title_sort | distributionally robust learning |
| volume_link | (DE-604)BV047879910 |
| work_keys_str_mv | AT chenruidi distributionallyrobustlearning AT paschalidisioannisch distributionallyrobustlearning |