kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Generalized Talagrand Inequality for Sinkhorn Distance using Entropy Power Inequality
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0003-0989-1682
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0002-7926-5081
2021 (English)In: 2021 IEEE Information Theory Workshop (ITW), Institute of Electrical and Electronics Engineers (IEEE) , 2021Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, we study the connection between entropic optimal transport and entropy power inequality (EPI). First, we prove an HWI-type inequality making use of the infinitesimal displacement convexity of optimal transport map. Second, we derive two Talagrand-type inequalities using the saturation of EPI that corresponds to a numerical term in our expression. We evaluate for a wide variety of distributions this term whereas for Gaussian and i.i.d. Cauchy distributions this term is found in explicit form. We show that our results extend previous results of Gaussian Talagrand inequality for Sinkhorn distance to the strongly log-concave case.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2021.
National Category
Other Engineering and Technologies
Identifiers
URN: urn:nbn:se:kth:diva-313697DOI: 10.1109/ITW48936.2021.9611464ISI: 000794133300084Scopus ID: 2-s2.0-85123399963OAI: oai:DiVA.org:kth-313697DiVA, id: diva2:1667427
Conference
2021 IEEE Information Theory Workshop (ITW2021) October 17-21, 2021, virtual event.
Note

QC 20220610

Part of proceedings: ISBN 978-1-6654-0312-2

Available from: 2022-06-10 Created: 2022-06-10 Last updated: 2022-06-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Wang, ShuchanStavrou, FotiosSkoglund, Mikael

Search in DiVA

By author/editor
Wang, ShuchanStavrou, FotiosSkoglund, Mikael
By organisation
Information Science and Engineering
Other Engineering and Technologies

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 25 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf