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 language | English |
---|---|
Title of host publication | HOTNETS 2024 - Proceedings of the 2024 3rd ACM Workshop on Hot Topics in Networks |
Publisher | Association for Computing Machinery, Inc |
Pages | 86-94 |
Number of pages | 9 |
ISBN (Electronic) | 9798400712722 |
State | Published - 18 Nov 2024 |
Event | 3rd ACM Workshop on Hot Topics in Networks, HOTNETS 2024 - Irvine, United States Duration: 18 Nov 2024 → 19 Nov 2024 |
Publication series
Name | HOTNETS 2024 - Proceedings of the 2024 3rd ACM Workshop on Hot Topics in Networks |
---|
Conference
Conference | 3rd ACM Workshop on Hot Topics in Networks, HOTNETS 2024 |
---|---|
Country/Territory | United States |
City | Irvine |
Period | 18/11/24 → 19/11/24 |
Bibliographical note
Publisher Copyright:© 2024 Copyright held by the owner/author(s).
Keywords
- Machine Learning for Systems
- Performance Analysis