Optimal transport for deep generative models: state of the art and research challenges

Viet Huynh; Dinh Phung

doi:10.24963/ijcai.2021/607

Optimal transport for deep generative models: state of the art and research challenges

Viet Huynh, Dinh Phung

Department of Data Science & AI

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

1 Citation (Scopus)

Abstract

Optimal transport has a long history in mathematics which was proposed by Gaspard Monge in the eighteenth century [Monge, 1781]. However, until recently, advances in optimal transport theory pave the way for its use in the AI community, particularly for formulating deep generative models. In this paper, we provide a comprehensive overview of the literature in the field of deep generative models using optimal transport theory with an aim of providing a systematic review as well as outstanding problems and more importantly, open research opportunities to use the tools from the established optimal transport theory in the deep generative model domain.

Original language	English
Title of host publication	Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Editors	Zhi-Hua Zhou
Place of Publication	Marina del Rey CA USA
Publisher	Association for the Advancement of Artificial Intelligence (AAAI)
Pages	4450-4457
Number of pages	8
ISBN (Electronic)	9780999241196
DOIs	https://doi.org/10.24963/ijcai.2021/607
Publication status	Published - 2021
Event	International Joint Conference on Artificial Intelligence 2021 - Virtual, Montreal, Canada Duration: 19 Aug 2021 → 27 Aug 2021 Conference number: 30th https://www.ijcai.org/proceedings/2021/ (Proceedings) https://ijcai-21.org (Website)

Publication series

Name	IJCAI International Joint Conference on Artificial Intelligence
Publisher	Association for the Advancement of Artificial Intelligence (AAAI)
ISSN (Print)	1045-0823

Conference

Conference	International Joint Conference on Artificial Intelligence 2021
Abbreviated title	IJCAI 2021
Country/Territory	Canada
City	Montreal
Period	19/08/21 → 27/08/21
Internet address	https://www.ijcai.org/proceedings/2021/ (Proceedings) https://ijcai-21.org (Website)

Keywords

Machine learning
General

Access to Document

10.24963/ijcai.2021/607

375242586-oaFinal published version, 389 KB

Cite this

Huynh, V., & Phung, D. (2021). Optimal transport for deep generative models: state of the art and research challenges. In Z-H. Zhou (Ed.), Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (pp. 4450-4457). (IJCAI International Joint Conference on Artificial Intelligence). Association for the Advancement of Artificial Intelligence (AAAI). https://doi.org/10.24963/ijcai.2021/607

Huynh, Viet ; Phung, Dinh. / Optimal transport for deep generative models : state of the art and research challenges. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. editor / Zhi-Hua Zhou. Marina del Rey CA USA : Association for the Advancement of Artificial Intelligence (AAAI), 2021. pp. 4450-4457 (IJCAI International Joint Conference on Artificial Intelligence).

@inproceedings{e58ea65b62b04faf8b8373b494bcae5d,

title = "Optimal transport for deep generative models: state of the art and research challenges",

abstract = "Optimal transport has a long history in mathematics which was proposed by Gaspard Monge in the eighteenth century [Monge, 1781]. However, until recently, advances in optimal transport theory pave the way for its use in the AI community, particularly for formulating deep generative models. In this paper, we provide a comprehensive overview of the literature in the field of deep generative models using optimal transport theory with an aim of providing a systematic review as well as outstanding problems and more importantly, open research opportunities to use the tools from the established optimal transport theory in the deep generative model domain.",

keywords = "Machine learning, General",

author = "Viet Huynh and Dinh Phung",

note = "Publisher Copyright: {\textcopyright} 2021 International Joint Conferences on Artificial Intelligence. All rights reserved.; International Joint Conference on Artificial Intelligence 2021, IJCAI 2021 ; Conference date: 19-08-2021 Through 27-08-2021",

year = "2021",

doi = "10.24963/ijcai.2021/607",

language = "English",

series = "IJCAI International Joint Conference on Artificial Intelligence",

publisher = "Association for the Advancement of Artificial Intelligence (AAAI)",

pages = "4450--4457",

editor = "Zhi-Hua Zhou",

booktitle = "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence",

address = "United States of America",

url = "https://www.ijcai.org/proceedings/2021/, https://ijcai-21.org",

}

Huynh, V & Phung, D 2021, Optimal transport for deep generative models: state of the art and research challenges. in Z-H Zhou (ed.), Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. IJCAI International Joint Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Marina del Rey CA USA, pp. 4450-4457, International Joint Conference on Artificial Intelligence 2021, Montreal, Quebec, Canada, 19/08/21. https://doi.org/10.24963/ijcai.2021/607

Optimal transport for deep generative models : state of the art and research challenges. / Huynh, Viet ; Phung, Dinh.

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. ed. / Zhi-Hua Zhou. Marina del Rey CA USA : Association for the Advancement of Artificial Intelligence (AAAI), 2021. p. 4450-4457 (IJCAI International Joint Conference on Artificial Intelligence).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Optimal transport for deep generative models

T2 - International Joint Conference on Artificial Intelligence 2021

AU - Huynh, Viet

AU - Phung, Dinh

N1 - Conference code: 30th

PY - 2021

Y1 - 2021

N2 - Optimal transport has a long history in mathematics which was proposed by Gaspard Monge in the eighteenth century [Monge, 1781]. However, until recently, advances in optimal transport theory pave the way for its use in the AI community, particularly for formulating deep generative models. In this paper, we provide a comprehensive overview of the literature in the field of deep generative models using optimal transport theory with an aim of providing a systematic review as well as outstanding problems and more importantly, open research opportunities to use the tools from the established optimal transport theory in the deep generative model domain.

AB - Optimal transport has a long history in mathematics which was proposed by Gaspard Monge in the eighteenth century [Monge, 1781]. However, until recently, advances in optimal transport theory pave the way for its use in the AI community, particularly for formulating deep generative models. In this paper, we provide a comprehensive overview of the literature in the field of deep generative models using optimal transport theory with an aim of providing a systematic review as well as outstanding problems and more importantly, open research opportunities to use the tools from the established optimal transport theory in the deep generative model domain.

KW - Machine learning

KW - General

UR - http://www.scopus.com/inward/record.url?scp=85125439867&partnerID=8YFLogxK

U2 - 10.24963/ijcai.2021/607

DO - 10.24963/ijcai.2021/607

M3 - Conference Paper

AN - SCOPUS:85125439867

T3 - IJCAI International Joint Conference on Artificial Intelligence

SP - 4450

EP - 4457

BT - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

A2 - Zhou, Zhi-Hua

PB - Association for the Advancement of Artificial Intelligence (AAAI)

CY - Marina del Rey CA USA

Y2 - 19 August 2021 through 27 August 2021

ER -

Huynh V , Phung D. Optimal transport for deep generative models: state of the art and research challenges. In Zhou Z-H, editor, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Marina del Rey CA USA: Association for the Advancement of Artificial Intelligence (AAAI). 2021. p. 4450-4457. (IJCAI International Joint Conference on Artificial Intelligence). https://doi.org/10.24963/ijcai.2021/607

Optimal transport for deep generative models: state of the art and research challenges

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this