Publication:
Optimal and efficient distributed online learning for big data

Placeholder

School / College / Institute

Organizational Unit

Program

KU Authors

Co-Authors

Sayın, Muhammed O.
Vanlı, N. Denizcan
Kozat, Süleyman S.

Publication Date

Language

Embargo Status

Journal Title

Journal ISSN

Volume Title

Alternative Title

Abstract

We propose optimal and efficient distributed online learning strategies for Big Data applications. Here, we consider the optimal state estimation over distributed network of autonomous data sources. The autonomous data sources can generate and process data locally irrespective of any centralized control unit. We seek to enhance the learning rate through the distributed control of those autonomous data sources. We emphasize that although this problem attracted significant attention and extensively studied in different fields including services computing and machine learning disciplines, all the well-known strategies achieve suboptimal online learning performance in the mean square error sense. To this end, we introduce the oracle algorithm as the optimal distributed online learning strategy. We also propose the optimal and efficient distributed online learning algorithm that reduces the communication load tremendously, i.e., requires the undirected disclosure of only a single scalar. Finally, we demonstrate the significant performance gains due to the proposed strategies with respect to the state-of-the-art approaches.

Source

Publisher

IEEE

Subject

Computer science, Theory methods, Engineering, Electrical electronic engineering

Citation

Has Part

Source

2015 IEEE International Congress on Big Data - Bigdata Congress 2015

Book Series Title

Edition

DOI

10.1109/BigDataCongress.2015.27

item.page.datauri

Link

Rights

Copyrights Note

Endorsement

Review

Supplemented By

Referenced By

0

Views

0

Downloads

View PlumX Details