Linear Regression over Networks with Communication Guarantees

Konstantinos Gatsis
Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:767-778, 2021.

Abstract

A key functionality of emerging connected autonomous systems such as smart cities, smart transportation systems, and the industrial Internet-of-Things, is the ability to process and learn from data collected at different physical locations. This is increasingly attracting attention under the terms of distributed learning and federated learning. However, in connected autonomous systems, data transfer takes place over communication networks with often limited resources. This paper examines algorithms for communication-efficient learning for linear regression tasks by exploiting the informativeness of the data. The developed algorithms enable a tradeoff between communication and learning with theoretical performance guarantees and efficient practical implementations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v144-gatsis21a, title = {Linear Regression over Networks with Communication Guarantees}, author = {Gatsis, Konstantinos}, booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control}, pages = {767--778}, year = {2021}, editor = {Jadbabaie, Ali and Lygeros, John and Pappas, George J. and A. Parrilo, Pablo and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie N.}, volume = {144}, series = {Proceedings of Machine Learning Research}, month = {07 -- 08 June}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v144/gatsis21a/gatsis21a.pdf}, url = {https://proceedings.mlr.press/v144/gatsis21a.html}, abstract = {A key functionality of emerging connected autonomous systems such as smart cities, smart transportation systems, and the industrial Internet-of-Things, is the ability to process and learn from data collected at different physical locations. This is increasingly attracting attention under the terms of distributed learning and federated learning. However, in connected autonomous systems, data transfer takes place over communication networks with often limited resources. This paper examines algorithms for communication-efficient learning for linear regression tasks by exploiting the informativeness of the data. The developed algorithms enable a tradeoff between communication and learning with theoretical performance guarantees and efficient practical implementations.} }
Endnote
%0 Conference Paper %T Linear Regression over Networks with Communication Guarantees %A Konstantinos Gatsis %B Proceedings of the 3rd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2021 %E Ali Jadbabaie %E John Lygeros %E George J. Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire J. Tomlin %E Melanie N. Zeilinger %F pmlr-v144-gatsis21a %I PMLR %P 767--778 %U https://proceedings.mlr.press/v144/gatsis21a.html %V 144 %X A key functionality of emerging connected autonomous systems such as smart cities, smart transportation systems, and the industrial Internet-of-Things, is the ability to process and learn from data collected at different physical locations. This is increasingly attracting attention under the terms of distributed learning and federated learning. However, in connected autonomous systems, data transfer takes place over communication networks with often limited resources. This paper examines algorithms for communication-efficient learning for linear regression tasks by exploiting the informativeness of the data. The developed algorithms enable a tradeoff between communication and learning with theoretical performance guarantees and efficient practical implementations.
APA
Gatsis, K.. (2021). Linear Regression over Networks with Communication Guarantees. Proceedings of the 3rd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 144:767-778 Available from https://proceedings.mlr.press/v144/gatsis21a.html.

Related Material