Introduction to the workshop [9:00 am- 9:15 am]
Workshop organizers: Behnaz Arzani and Bita Rouhani
Keynote [9:15 am - 9:45 am]
Title: The agony and the ecstasy of machine learning over the Internet
Abstract: Many networking settings ask us, or really our computers, to make tough decisions from partial information: congestion control, traffic engineering, provisioning, channel characterization, scheduling, query planning, spam filtering, video streaming, predicting real-life indicators from crowdsourced information, etc. This suggests a natural setting for machine learning, which has shown great success in adjacent areas of computer science. And yet -- and yet! The Internet has turned out to be a particularly challenging setting for ML. We don't know how to simulate it, which makes it challenging to learn reliable control algorithms. It's hard to measure loss functions on a distributed network where each node receives only partial information. And we have a hard time learning algorithms that are robust to adversarial input. I'll present findings from two multi-year deployments of ML over the Internet, for congestion control and video streaming, and discuss where I think there's cause for optimism and caution.
Discussion panel (part 1) [9:45-10:30]
Panelists: Victor Bahl (Microsoft Research), Nicolo Fusi (Microsoft Research Cambridge), Ranjita Bhagwan (Microsoft Research India), Navendu Jain (Microsoft), Keith Winstein (Stanford)
In the first panel session, we will begin with a set of questions from the workshop organizers and a discussion between panelists.
Discussion panel (part 2) [11:00-12:00]
Accepted talks [1:30-2:30]
Taurus: An Intelligent Data PlaneTushar Swamy (Stanford University), Alexander Rucker (Stanford University), Muhammad Shahbaz (Stanford University), and Kunle Olukotun (Stanford University)Automating Botnet Detection with Graph Neural NetworksJiawei Zhou (Harvard University), Zhiying Xu (Harvard University), Alexander Rush (Cornell University), Minlan Yu (Harvard University)
Invited talks [3:00-4:00]
Daniel Berger (Experience with developing ML for distributed caching systems)
Amar Phanishayee (Project Fiddle: Fast & Efficient Infrastructure for Distributed Deep Learning)