Stochastic wasserstein barycenters

Sebastian Claici; Edward Chien; Justin Solomon

Stochastic wasserstein barycenters

Sebastian Claici, Edward Chien, Justin Solomon

Massachusetts Institute of Technology

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

21 Scopus citations

Abstract

Wi present a stochastic algorithm to compute the baryccntcr of a set of probability distributions under the Wasscrstcin metric from optimal transport Unlike previous approaches,our method extends to continuous input distributions and allows the support of the baryccntcr to be adjusted in each iteration. VVc tacklc the problem without rcgu- larization, allowing us to rccovcr a much sharper output; We give examples where our algorithm recovers a more meaningful baryccntcr than previous work. Our method is versatile and can be extended to applications such as generating super samples from a given distribution and recovering blue noise approximations.

Original language	English
Title of host publication	35th International Conference on Machine Learning, ICML 2018
Editors	Andreas Krause, Jennifer Dy
Publisher	International Machine Learning Society (IMLS)
Pages	1627-1636
Number of pages	10
ISBN (Electronic)	9781510867963
State	Published - 2018
Externally published	Yes
Event	35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden Duration: 10 Jul 2018 → 15 Jul 2018

Publication series

Name	35th International Conference on Machine Learning, ICML 2018
Volume	3

Conference

Conference	35th International Conference on Machine Learning, ICML 2018
Country/Territory	Sweden
City	Stockholm
Period	10/07/18 → 15/07/18

Bibliographical note

Publisher Copyright:
© 2018 35th International Conference on Machine Learning, ICML 2018. All rights reserved.

Funding

The authors thank Fernando de Goes, Marco Cuturi, Gabriel Peyre, and Matthew Staib for input and early discussions. The authors acknowledge the generous support of Army Research Office grant W911NF-12-R0011 (Smooth Modeling of Flows on Graphs), from the MIT Research Support Committee, from the MIT-IBM Watson AI Lab, from the Skoltech-MIT Next Generation Program, and from an Amazon Research Award.

Funders	Funder number
Army Research Office	W911NF-12-R0011
Massachusetts Institute of Technology

Cite this

@inproceedings{f61644507a2243779dc17e63f6696200,

title = "Stochastic wasserstein barycenters",

abstract = "Wi present a stochastic algorithm to compute the baryccntcr of a set of probability distributions under the Wasscrstcin metric from optimal transport Unlike previous approaches,our method extends to continuous input distributions and allows the support of the baryccntcr to be adjusted in each iteration. VVc tacklc the problem without rcgu- larization, allowing us to rccovcr a much sharper output; We give examples where our algorithm recovers a more meaningful baryccntcr than previous work. Our method is versatile and can be extended to applications such as generating super samples from a given distribution and recovering blue noise approximations.",

author = "Sebastian Claici and Edward Chien and Justin Solomon",

note = "Publisher Copyright: {\textcopyright} 2018 35th International Conference on Machine Learning, ICML 2018. All rights reserved.; 35th International Conference on Machine Learning, ICML 2018 ; Conference date: 10-07-2018 Through 15-07-2018",

year = "2018",

language = "אנגלית",

series = "35th International Conference on Machine Learning, ICML 2018",

publisher = "International Machine Learning Society (IMLS)",

pages = "1627--1636",

editor = "Andreas Krause and Jennifer Dy",

booktitle = "35th International Conference on Machine Learning, ICML 2018",

}

Claici, S, Chien, E & Solomon, J 2018, Stochastic wasserstein barycenters. in A Krause & J Dy (eds), 35th International Conference on Machine Learning, ICML 2018. 35th International Conference on Machine Learning, ICML 2018, vol. 3, International Machine Learning Society (IMLS), pp. 1627-1636, 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, 10/07/18.

Stochastic wasserstein barycenters. / Claici, Sebastian; Chien, Edward; Solomon, Justin.
35th International Conference on Machine Learning, ICML 2018. ed. / Andreas Krause; Jennifer Dy. International Machine Learning Society (IMLS), 2018. p. 1627-1636 (35th International Conference on Machine Learning, ICML 2018; Vol. 3).

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

TY - GEN

T1 - Stochastic wasserstein barycenters

AU - Claici, Sebastian

AU - Chien, Edward

AU - Solomon, Justin

PY - 2018

Y1 - 2018

N2 - Wi present a stochastic algorithm to compute the baryccntcr of a set of probability distributions under the Wasscrstcin metric from optimal transport Unlike previous approaches,our method extends to continuous input distributions and allows the support of the baryccntcr to be adjusted in each iteration. VVc tacklc the problem without rcgu- larization, allowing us to rccovcr a much sharper output; We give examples where our algorithm recovers a more meaningful baryccntcr than previous work. Our method is versatile and can be extended to applications such as generating super samples from a given distribution and recovering blue noise approximations.

AB - Wi present a stochastic algorithm to compute the baryccntcr of a set of probability distributions under the Wasscrstcin metric from optimal transport Unlike previous approaches,our method extends to continuous input distributions and allows the support of the baryccntcr to be adjusted in each iteration. VVc tacklc the problem without rcgu- larization, allowing us to rccovcr a much sharper output; We give examples where our algorithm recovers a more meaningful baryccntcr than previous work. Our method is versatile and can be extended to applications such as generating super samples from a given distribution and recovering blue noise approximations.

UR - http://www.scopus.com/inward/record.url?scp=85056566070&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85056566070

T3 - 35th International Conference on Machine Learning, ICML 2018

SP - 1627

EP - 1636

BT - 35th International Conference on Machine Learning, ICML 2018

A2 - Krause, Andreas

A2 - Dy, Jennifer

PB - International Machine Learning Society (IMLS)

T2 - 35th International Conference on Machine Learning, ICML 2018

Y2 - 10 July 2018 through 15 July 2018

ER -

Stochastic wasserstein barycenters

Abstract

Publication series

Conference

Bibliographical note

Funding

Other files and links

Fingerprint

Cite this