Canopy: Property-Driven Learning for Congestion Control

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Chenxi, Saxena, Divyanshu, Dwivedula, Rohit, Mahajan, Kshiteej, Chaudhuri, Swarat, Akella, Aditya
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912815460122624
author Yang, Chenxi
Saxena, Divyanshu
Dwivedula, Rohit
Mahajan, Kshiteej
Chaudhuri, Swarat
Akella, Aditya
author_facet Yang, Chenxi
Saxena, Divyanshu
Dwivedula, Rohit
Mahajan, Kshiteej
Chaudhuri, Swarat
Akella, Aditya
contents Learning-based congestion controllers offer better adaptability compared to traditional heuristics. However, the unreliability of learning techniques can cause learning-based controllers to behave poorly, creating a need for formal guarantees. While methods for formally verifying learned congestion controllers exist, these methods offer binary feedback that cannot optimize the controller toward better behavior. We improve this state-of-the-art via Canopy, a new property-driven framework that integrates learning with formal reasoning in the learning loop. Canopy uses novel quantitative certification with an abstract interpreter to guide the training process, rewarding models, and evaluating robust and safe model performance on worst-case inputs. Our evaluation demonstrates that unlike state-of-the-art learned controllers, Canopy-trained controllers provide both adaptability and worst-case reliability across a range of network conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10915
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Canopy: Property-Driven Learning for Congestion Control
Yang, Chenxi
Saxena, Divyanshu
Dwivedula, Rohit
Mahajan, Kshiteej
Chaudhuri, Swarat
Akella, Aditya
Machine Learning
Networking and Internet Architecture
Learning-based congestion controllers offer better adaptability compared to traditional heuristics. However, the unreliability of learning techniques can cause learning-based controllers to behave poorly, creating a need for formal guarantees. While methods for formally verifying learned congestion controllers exist, these methods offer binary feedback that cannot optimize the controller toward better behavior. We improve this state-of-the-art via Canopy, a new property-driven framework that integrates learning with formal reasoning in the learning loop. Canopy uses novel quantitative certification with an abstract interpreter to guide the training process, rewarding models, and evaluating robust and safe model performance on worst-case inputs. Our evaluation demonstrates that unlike state-of-the-art learned controllers, Canopy-trained controllers provide both adaptability and worst-case reliability across a range of network conditions.
title Canopy: Property-Driven Learning for Congestion Control
topic Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2412.10915