End-to-End Performance Analysis of Learning-enabled Systems

Pooria Namyar, Michael Schapira, Ramesh Govindan, Santiago Segarra*, Ryan Beckett, Siva Kesava Reddy Kakarla, Behnaz Arzani

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose a performance analysis tool for learning-enabled systems that allows operators to uncover potential performance issues before deploying DNNs in their systems. The tools that exist for this purpose require operators to faithfully model all components (a white-box approach) or do inefficient black-box local search. We propose a gray-box alternative, which eliminates the need to precisely model all the system’s components. Our approach is faster and finds substantially worse scenarios compared to prior work. We show that a state-of-the-art learning-enabled traffic engineering pipeline can underperform the optimal by 6× — a much higher number compared to what the authors found.

Original languageEnglish
Title of host publicationHOTNETS 2024 - Proceedings of the 2024 3rd ACM Workshop on Hot Topics in Networks
PublisherAssociation for Computing Machinery, Inc
Pages86-94
Number of pages9
ISBN (Electronic)9798400712722
StatePublished - 18 Nov 2024
Event3rd ACM Workshop on Hot Topics in Networks, HOTNETS 2024 - Irvine, United States
Duration: 18 Nov 202419 Nov 2024

Publication series

NameHOTNETS 2024 - Proceedings of the 2024 3rd ACM Workshop on Hot Topics in Networks

Conference

Conference3rd ACM Workshop on Hot Topics in Networks, HOTNETS 2024
Country/TerritoryUnited States
CityIrvine
Period18/11/2419/11/24

Bibliographical note

Publisher Copyright:
© 2024 Copyright held by the owner/author(s).

Keywords

  • Machine Learning for Systems
  • Performance Analysis

Fingerprint

Dive into the research topics of 'End-to-End Performance Analysis of Learning-enabled Systems'. Together they form a unique fingerprint.

Cite this