Online Service Providers in the Era of Data-driven Algorithms

Over the last few years, online service providers, e.g., Google and Facebook, have expanded their infrastructure beyond data centers to include edge networks and client-side devices (via mobile applications). While this growth has provided an unparalleled level of access to networking data and control over the infrastructure, most providers only leverage a small fraction of this potential. In this talk, I will describe the systematic challenges (both systems and algorithmic) that prevent online providers from unlocking this potential and illustrate how the use of data-driven algorithms enables these providers to utilize their networking infrastructure better. I will also describe the grander challenges that arise when online providers embrace data-driven approaches over traditional heuristics and discuss principled methods to address these broader challenges.

Bio: Theo is an assistant professor in the Department of Computer Science at Brown University. His group works on designing frameworks and algorithms for solving networking problems, speeding up the Internet, improving network reliability, and simplifying network management. He has won multiple awards, including best paper awards, AppliedNnetwork Research Prize, Yahoo!, Google, Facebook Faculty Awards, and an NSF Career award.