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
Delay-agnostic Asynchronous Coordinate Update Algorithm
KTH Royal Institute of Technology, Stockholm, Sweden.
KTH Royal Institute of Technology, Stockholm, Sweden.
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.ORCID iD: 0000-0002-6617-8683
KTH Royal Institute of Technology, Stockholm, Sweden.
Number of Authors: 42023 (English)In: ICML'23: Proceedings of Machine Learning Research / [ed] Andreas Krause; Emma Brunskill; Kyunghyun Cho; Barbara Engelhardt; Sivan Sabato; Jonathan Scarlett, 2023, p. 37582-37606Conference paper, Published paper (Refereed)
Abstract [en]

We propose a delay-agnostic asynchronous coordinate update algorithm (DEGAS) for computing operator fixed points, with applications to asynchronous optimization. DEGAS includes novel asynchronous variants of ADMM and block-coordinate descent as special cases. We prove that DEGAS converges with both bounded and unbounded delays under delay-free parameter conditions. We also validate by theory and experiments that DEGAS adapts well to the actual delays. The effectiveness of DEGAS is demonstrated by numerical experiments on classification problems.

Place, publisher, year, edition, pages
2023. p. 37582-37606
Series
Proceedings of Machine Learning Research (PMLR), E-ISSN 2640-3498 ; 202
National Category
Computer Sciences
Research subject
Computer and Systems Sciences
Identifiers
URN: urn:nbn:se:su:diva-222623OAI: oai:DiVA.org:su-222623DiVA, id: diva2:1804775
Conference
ICML'23: International Conference on Machine Learning, Honolulu Hawaii, USA, July 23 - 29, 2023.
Available from: 2023-10-13 Created: 2023-10-13 Last updated: 2023-10-16Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Länk till publikationen

Authority records

Magnússon, Sindri

Search in DiVA

By author/editor
Magnússon, Sindri
By organisation
Department of Computer and Systems Sciences
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 12 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