Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • 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
Provable reduction in communication rounds for non-smooth convex federated learning
Umeå University, Faculty of Science and Technology, Department of Computing Science.
Umeå University, Faculty of Science and Technology, Department of Mathematics and Mathematical Statistics.ORCID iD: 0000-0003-1134-2615
Umeå University, Faculty of Science and Technology, Department of Mathematics and Mathematical Statistics.ORCID iD: 0000-0001-7320-1506
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0001-7119-7646
2025 (English)In: 2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP), IEEE, 2025Conference paper, Published paper (Refereed)
Abstract [en]

Multiple local steps are key to communication-efficient federated learning. However, theoretical guarantees for such algorithms, without data heterogeneity-bounding assumptions, have been lacking in general non-smooth convex problems. Leveraging projection-efficient optimization methods, we propose FedMLS, a federated learning algorithm with provable improvements from multiple local steps. FedMLS attains an ϵ-suboptimal solution in O(1/ϵ) communication rounds, requiring a total of O(1/ϵ2) stochastic subgradient oracle calls.

Place, publisher, year, edition, pages
IEEE, 2025.
Series
Machine learning for signal processing, ISSN 1551-2541, E-ISSN 2161-0371
National Category
Computer Sciences Artificial Intelligence Algorithms
Identifiers
URN: urn:nbn:se:umu:diva-246282DOI: 10.1109/MLSP62443.2025.11204301ISBN: 979-8-3315-7030-9 (print)ISBN: 979-8-3315-7029-3 (electronic)OAI: oai:DiVA.org:umu-246282DiVA, id: diva2:2012696
Conference
2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP), Istanbul, Turkiye, August 31 - September 3, 2025
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)Available from: 2025-11-10 Created: 2025-11-10 Last updated: 2025-11-21Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records

Palenzuela, KarloDadras, AliYurtsever, AlpLöfstedt, Tommy

Search in DiVA

By author/editor
Palenzuela, KarloDadras, AliYurtsever, AlpLöfstedt, Tommy
By organisation
Department of Computing ScienceDepartment of Mathematics and Mathematical Statistics
Computer SciencesArtificial IntelligenceAlgorithms

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 42 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • 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