Chenxi Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Chenxi Yang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Aditya Akella
The University of Texas at Austin, Austin, TX, USA
1 shared publication - Divyanshu Saxena
The University of Texas at Austin, Austin, USA
1 shared publication - Kshiteej Mahajan
Google Deepmind, Mountain View, USA
1 shared publication - Rohit Dwivedula
UT Austin, Austin, USA
1 shared publication - Swarat Chaudhuri
University of Texas at Austin
1 shared publication
Latest Publications
- Open Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1658-1673
Canopy: Property-Driven Learning for Congestion Control
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.
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1658-1673
Open AccessCanopy: Property-Driven Learning for Congestion Control
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.