Learning Cost Functions for Optimal Transport
Inverse optimal transport (OT) refers to the problem of learning the cost function for OT from observed transport plan or its samples. In this paper, we derive an unconstrained convex optimization formulation of the inverse OT problem, which can be further augmented by any customizable regularizatio...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
05.07.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Inverse optimal transport (OT) refers to the problem of learning the cost function for OT from observed transport plan or its samples. In this paper, we derive an unconstrained convex optimization formulation of the inverse OT problem, which can be further augmented by any customizable regularization. We provide a comprehensive characterization of the properties of inverse OT, including uniqueness of solutions. We also develop two numerical algorithms, one is a fast matrix scaling method based on the Sinkhorn-Knopp algorithm for discrete OT, and the other one is a learning based algorithm that parameterizes the cost function as a deep neural network for continuous OT. The novel framework proposed in the work avoids repeatedly solving a forward OT in each iteration which has been a thorny computational bottleneck for the bi-level optimization in existing inverse OT approaches. Numerical results demonstrate promising efficiency and accuracy advantages of the proposed algorithms over existing state-of-the-art methods. |
---|---|
AbstractList | Inverse optimal transport (OT) refers to the problem of learning the cost function for OT from observed transport plan or its samples. In this paper, we derive an unconstrained convex optimization formulation of the inverse OT problem, which can be further augmented by any customizable regularization. We provide a comprehensive characterization of the properties of inverse OT, including uniqueness of solutions. We also develop two numerical algorithms, one is a fast matrix scaling method based on the Sinkhorn-Knopp algorithm for discrete OT, and the other one is a learning based algorithm that parameterizes the cost function as a deep neural network for continuous OT. The novel framework proposed in the work avoids repeatedly solving a forward OT in each iteration which has been a thorny computational bottleneck for the bi-level optimization in existing inverse OT approaches. Numerical results demonstrate promising efficiency and accuracy advantages of the proposed algorithms over existing state-of-the-art methods. |
Author | Zha, Hongyuan Ye, Xiaojing Ma, Shaojun Zhou, Haomin Sun, Haodong |
Author_xml | – sequence: 1 givenname: Shaojun surname: Ma fullname: Ma, Shaojun – sequence: 2 givenname: Haodong surname: Sun fullname: Sun, Haodong – sequence: 3 givenname: Xiaojing surname: Ye fullname: Ye, Xiaojing – sequence: 4 givenname: Hongyuan surname: Zha fullname: Zha, Hongyuan – sequence: 5 givenname: Haomin surname: Zhou fullname: Zhou, Haomin |
BookMark | eNqNyrEKwjAQgOEgClbtOwScCzXXtHYuFgfBpXsJkkpKvYu55P118AGc_uH7d2KNhHYlMgVwKs6VUluRM89lWaq6UVpDJoqbNQEdPmVHHGWf8BEdIcuJgrz76F5mkUMwyJ5CPIjNZBa2-a97cewvQ3ctfKB3shzHmVLAL40KatBNBW0L_10f7Q4z4g |
ContentType | Paper |
Copyright | 2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_23635743993 |
IEDL.DBID | BENPR |
IngestDate | Tue Sep 24 20:21:02 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_23635743993 |
OpenAccessLink | https://www.proquest.com/docview/2363574399/abstract/?pq-origsite=%requestingapplication% |
PQID | 2363574399 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2363574399 |
PublicationCentury | 2000 |
PublicationDate | 20210705 |
PublicationDateYYYYMMDD | 2021-07-05 |
PublicationDate_xml | – month: 07 year: 2021 text: 20210705 day: 05 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2021 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.3314888 |
SecondaryResourceType | preprint |
Snippet | Inverse optimal transport (OT) refers to the problem of learning the cost function for OT from observed transport plan or its samples. In this paper, we derive... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Algorithms Artificial neural networks Computational geometry Convexity Cost function Iterative methods Machine learning Neural networks Optimization Regularization Transportation planning |
Title | Learning Cost Functions for Optimal Transport |
URI | https://www.proquest.com/docview/2363574399/abstract/ |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LSwMxEB7aLoI3n_ioJaDXsO0m3cdJsOy6CK1FFHoreXpR-9j16m83E3brQegxBJIhTGa-fDOZAbjjQjPmYDi1iWSUq9TSLNZDOrQ2SgXLhPHZhNNZXL7xp8V40YGy_QuDaZWtTfSGWq8UcuRhxLByGqLnUEhkAVQd3q83FPtHYZy1aabRhSAacQzYBg_5bP6y41uiOHHomf0zud6PFEcQzMXabI-hY75O4MCnX6rqFGhT5vSdTFZVTQrnbLw-EAcpybO71Z_ig-zqkJ_BbZG_Tkra7rFsNKJa_snPzqHnnvbmAojGenFOLJsllmdGSS1ZLDJpYynYSJtL6O9b6Wr_9DUcRpiBgWTkuA-9evttbpwLreUAumnxOGjOyI2mP_kv_yB8Xw |
link.rule.ids | 786,790,12792,21416,33408,33779,43635,43840 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1NTwMhEJ1oG6M360esViXRK7EulC0nD43rVtvqoSa9bWABL2o_dv3_MoTWg0nPJDAhw8xjeLwBuOXKMOZhOHWpZpSXfUelMF3adS7pKyaVDWzC8UTk7_x51pvFglsVaZXrmBgCtZmXWCO_SxgqpyF6flgsKXaNwtfV2EJjF5ocx_GnePa0qbEkIvWImf0LsyF3ZIfQfFMLu2rBjv0-gr1AuSyrY6BR2vSDDOZVTTKfYIIPEA8jyas_yV_qk2y0x0_gJnucDnK6XqOIXlAVfzazU2j467w9A2JQI86b5WTquLSlNpoJJbUTWrF7Y9vQ2TbT-fbha9jPp-NRMRpOXi7gIEEGBhYjex1o1Ksfe-lTaK2vwj79AgydeBU |
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=Learning+Cost+Functions+for+Optimal+Transport&rft.jtitle=arXiv.org&rft.au=Ma%2C+Shaojun&rft.au=Sun%2C+Haodong&rft.au=Ye%2C+Xiaojing&rft.au=Zha%2C+Hongyuan&rft.date=2021-07-05&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |