BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Learning-Powered Networked Systems - Michael Schapira (Heb
 rew University of Jerusalem)
DTSTART:20240206T130000Z
DTEND:20240206T140000Z
UID:TALK208372@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:Recent years have witnessed a surge of interest in applying id
 eas 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-lear
 ning-based approach for optimizing traffic flow between data centers. Time
  permitting\, I will also discuss recent results on how the safe real-worl
 d deployment of such learning-augmented systems can be accomplished.\n\n*B
 io:*\nMichael Schapira is professor of Computer Science at Hebrew Universi
 ty. His current research interests lie at applying ideas and machinery fro
 m ML to computer systems. Prior to joining Hebrew U\, he was a visiting sc
 ientist at Google NYC's Infrastructure Networking Group and a postdoctoral
  researcher at UC Berkeley\, Yale University\, and Princeton University. H
 e is a recipient of the Wolf Foundation's Krill Prize\, faculty awards fro
 m Microsoft\, Google\, and Facebook\, IETF/IRTF Applied Networking Researc
 h Prizes\, the IEEE Communications Society William R. Bennett Prize\, and 
 the NSDI 2023 Best Paper Award.\n\n"You can also join us on Zoom":https://
 cam-ac-uk.zoom.us/j/92041617729
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR