Abstract

Recent years have witnessed a surge of interest in applying ideas and machinery from machine learning to the design of networked systems. I will discuss my recent efforts to incorporate learning in the context of two fundamental computer networking challenges: routing and congestion control. Specifically, I will discuss applications of deep reinforcement learning to the Internet congestion control domain and a novel, deep-learning-based approach for optimizing traffic flow between data centers. Time permitting, I will also discuss recent results on how the safe real-world deployment of such learning-augmented systems can be accomplished.

Bio: Michael Schapira is professor of Computer Science at Hebrew University. His current research interests lie at applying ideas and machinery from ML to computer systems. Prior to joining Hebrew U, he was a visiting scientist at Google NYC ’s Infrastructure Networking Group and a postdoctoral researcher at UC Berkeley, Yale University, and Princeton University. He is a recipient of the Wolf Foundation’s Krill Prize, faculty awards from Microsoft, Google, and Facebook, IETF /IRTF Applied Networking Research Prizes, the IEEE Communications Society William R. Bennett Prize, and the NSDI 2023 Best Paper Award.

You can also join us on Zoom