Session

Understanding and Improving Robustness of Networked Systems With Machine Learning

Speaker

Brighten Godfrey

University of Illinois at Urbana-Champaign and Broadcom
The keynote speaker Brighten Godfrey
Brighten Godfrey is a Professor in the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign. He co-founded and served as CTO of network verification pioneer Veriflow through its 2019 acquisition by VMware (now Broadcom) . He received his Ph.D. at UC Berkeley in 2009, and his B.S. at Carnegie Mellon University in 2002. His research interests lie in the design of networked systems and algorithms. He has served as co-chair of ACM SIGCOMM 2022, SOSR 2016 and ACM HotNets 2014, and currently serves on the ACM SIGCOMM Steering Committee. He is a winner of the ACM SIGCOMM Rising Star Award, the Sloan Research Fellowship, and the National Science Foundation CAREER Award.

Session Type

Keynote

Description

Networks are infrastructure, and we need infrastructure to perform reliably. But networked systems are also complicated and difficult to fully observe or understand, even for their own designers and operators. In this talk we’ll explore how machine learning might provide an approach to understand the systems and protocols we have built and ultimately improve their robustness. We will discuss using machine learning as an adversary to discover environments where congestion control implementations perform poorly, and automatically diagnosing performance problems in distributed cloud applications, before concluding with future directions.