Online Distributed Optimization with Efficient Communication via Temporal Similarity

Juncheng Wang, Ben Liang, Min Dong, Gary Boudreau, Ali Afana

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review


We consider online distributed optimization in a networked system, where multiple devices assisted by a server collaboratively minimize the accumulation of a sequence of global loss functions that can vary over time. To reduce the amount of communication, the devices send quantized and compressed local decisions to the server, resulting in noisy global decisions. Therefore, there exists a tradeoff between the optimization performance and the communication overhead. Existing works separately optimize computation and communication. In contrast, we jointly consider computation and communication over time, by encouraging temporal similarity in the decision sequence to control the communication overhead. We propose an efficient algorithm, termed Online Distributed Optimization with Temporal Similarity (ODOTS), where the local decisions are both computation- and communication-aware. Furthermore, ODOTS uses a novel tunable virtual queue, which completely removes the commonly assumed Slater’s condition through a modified Lyapunov drift analysis. ODOTS delivers provable performance bounds on both the optimization objective and constraint violation. As an example application, we apply ODOTS to enable communication-efficient federated learning. Our experimental results based on real-world image classification demonstrate that ODOTS obtains higher classification accuracy and lower communication overhead compared with the current best alternatives for both convex and non-convex loss functions.
Original languageEnglish
Title of host publicationIEEE INFOCOM 2023 - IEEE Conference on Computer Communications
Number of pages10
ISBN (Electronic)9781665403252
ISBN (Print)9781665431316
Publication statusPublished - May 2023
Event42rd IEEE Conference on Computer Communications, IEEE INFOCOM 2023 - New York, United States
Duration: 17 May 202320 May 2023

Publication series

NameProceedings of IEEE Conference on Computer Communications
ISSN (Print)0743-166X
ISSN (Electronic)2641-9874


Competition42rd IEEE Conference on Computer Communications, IEEE INFOCOM 2023
Country/TerritoryUnited States
CityNew York
Internet address

Scopus Subject Areas

  • Electrical and Electronic Engineering
  • Computer Science(all)

User-Defined Keywords

  • Communication-efficient federated learning
  • Distributed learning
  • Long-term constraints
  • Online distributed optimization


Dive into the research topics of 'Online Distributed Optimization with Efficient Communication via Temporal Similarity'. Together they form a unique fingerprint.

Cite this