Machine Learning Model Updates in Edge Computing: An Optimal Stopping Theory Approach

Aleksandrova, E., Anagnostopoulos, C. and Kolomvatsos, K. (2019) Machine Learning Model Updates in Edge Computing: An Optimal Stopping Theory Approach. In: 18th IEEE International Symposium on Parallel and Distributed Computing (ISPDC 2019), Amsterdam, The Netherlands, 5-7 Jun 2019, ISBN 9781728138015 (doi: 10.1109/ISPDC.2019.000-4)

184450.pdf - Accepted Version



This work studies a sequential decision making methodology of when to update machine learning models in Edge Computing environments given underlying changes in the contextual data distribution. The proposed model focuses on updates scheduling and takes into consideration the optimal decision time for minimizing the network overhead. At the same time it preserves the prediction accuracy of models based on the principles of the Optimal Stopping Theory (OST). The paper reports on a comparative analysis between the proposed approach and other policies proposed in the respective literature while providing an evaluation of the performances using linear and support vector regression models. Our evaluation process is realized over real contextual data streams to reveal the strengths and weaknesses of the proposed strategy.

Item Type:Conference Proceedings
Additional Information:This research is funded by EU-H2020 GNFUV (#Grant 645220) and EU-H2020 MSCA INNOVATE (#Grant 745829).
Glasgow Author(s) Enlighten ID:Kolomvatsos, Dr Kostas and Anagnostopoulos, Dr Christos and Aleksandrova, Ms Ekaterina
Authors: Aleksandrova, E., Anagnostopoulos, C., and Kolomvatsos, K.
College/School:College of Science and Engineering > School of Computing Science
Copyright Holders:Copyright © 2019 IEEE
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record