Abstract:
Machine learning (ML) has deeply impacted many subareas of computer science, including computer vision, natural language processing, computational biology, and more. Yet, computer networking has largely withstood the ML tide until recently. Recent advances suggest that this might be changing. We ask whether/when network protocol design, which traditionally relies on the application of algorithmic insights by human experts, can be replaced by a data-driven, ML-guided approach. We will investigate this question in the context of two fundamental networking challenges: routing and congestion control.
Speaker Bio:
Michael Schapira is an associate professor of Computer Science at the Hebrew University of Jerusalem. His research lies in the area of computer networking and spans ML-informed network protocols, next-generation network architectures, and network security. Prior to joining the Hebrew U, he was a visiting scientist at Google NYC and a postdoctoral researcher at UC Berkeley, Yale, and Princeton. He is a recipient of the Microsoft Research Faculty Fellowship, ERC Starting Grant, IETF/IRTF Applied Networking Research Prizes, and Google Faculty Research Award.
