Data-driven Distributionally Robust Optimization for Edge Intelligence

Zhaofeng Zhang, Sen Lin, Mehmet Dedeoglu, Kemi Ding, Junshan Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations


The past few years have witnessed the explosive growth of Internet of Things (IoT) devices. The necessity of real-time edge intelligence for IoT applications demands that decision making must take place right here right now at the network edge, thus dictating that a high percentage of the IoT created data should be stored and analyzed locally. However, the computing resources are constrained and the amount of local data is often very limited at edge nodes. To tackle these challenges, we propose a distributionally robust optimization (DRO)-based edge intelligence framework, which is based on an innovative synergy of cloud knowledge transfer and local learning. More specifically, the knowledge transfer from the cloud learning is in the form of a reference distribution and its associated uncertainty set. Further, based on its local data, the edge device constructs an uncertainty set centered around its empirical distribution. The edge learning problem is then cast as a DRO problem subject to the above two distribution uncertainty sets. Building on this framework, we investigate two problem formulations for DRO-based edge intelligence, where the uncertainty sets are constructed using the Kullback-Leibler divergence and the Wasserstein distance, respectively. Numerical results demonstrate the effectiveness of the proposed DRO-based framework.

Original languageEnglish (US)
Title of host publicationINFOCOM 2020 - IEEE Conference on Computer Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages10
ISBN (Electronic)9781728164120
StatePublished - Jul 2020
Event38th IEEE Conference on Computer Communications, INFOCOM 2020 - Toronto, Canada
Duration: Jul 6 2020Jul 9 2020

Publication series

NameProceedings - IEEE INFOCOM
ISSN (Print)0743-166X


Conference38th IEEE Conference on Computer Communications, INFOCOM 2020


  • Edge intelligence
  • Kullback-Leibler divergence
  • Wasserstein distance
  • collaborative learning
  • distributionally robust optimization

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering


Dive into the research topics of 'Data-driven Distributionally Robust Optimization for Edge Intelligence'. Together they form a unique fingerprint.

Cite this