Augment Decentralized Online Convex Optimization with Arbitrarily Bad Machine-Learned Predictions

Dacheng Wen, Yupeng Li, Francis C.M. Lau

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

Abstract

Decentralized online convex optimization (DOCO), as a pivotal computational paradigm in machine learning, has been applied to many critical tasks. However, existing DOCO algorithms, due to their excessive emphasis on the worst-case theoretical performance, appear to be overly cautious in making decisions across all possible cases, especially in real-world applications where the worst cases actually hardly occur. Therefore, these existing approaches typically are limited in performance in practice. To avoid such pessimistic strategies, we propose to study the approach of augmenting DOCO with machine-learned predictions that can guide the decision-making process. We present an overview of the problem along with the preliminary results and outlook in this work.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE 44th International Conference on Distributed Computing Systems, ICDCS 2024
PublisherIEEE
Pages1460-1461
Number of pages2
ISBN (Electronic)9798350386059
DOIs
Publication statusPublished - 23 Jul 2024
Event44th IEEE International Conference on Distributed Computing Systems, ICDCS 2024 - Jersey City, United States
Duration: 23 Jul 202426 Jul 2024
https://icdcs2024.icdcs.org/
https://icdcs2024.icdcs.org/accepted-papers/
https://ieeexplore.ieee.org/xpl/conhome/10630852/proceeding

Publication series

NameProceedings - International Conference on Distributed Computing Systems
ISSN (Print)1063-6927
ISSN (Electronic)2575-8411

Conference

Conference44th IEEE International Conference on Distributed Computing Systems, ICDCS 2024
Country/TerritoryUnited States
CityJersey City
Period23/07/2426/07/24
Internet address

Scopus Subject Areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Augment Decentralized Online Convex Optimization with Arbitrarily Bad Machine-Learned Predictions'. Together they form a unique fingerprint.

Cite this