Colloquium Details
Towards a Smarter Cloud with Data
| Author: | Hongqiang "Harry" Liu Microsoft Research, Redmond, WA |
|---|---|
| Date: | May 04, 2017 |
| Time: | 15:30 |
| Location: | 220 Deschutes |
| Host: | Lei Jiao |
Abstract
Cloud has been becoming an indispensable infrastructure of human-being. Like other basic infrastructures, e.g. water, electricity, Internet, etc., cost and availability are the most critical properties of cloud for cloud users and cloud providers. This talk highlights the presenter's recent efforts on reducing the cost and enhancing the availability for Microsoft Azure; It them motivates the vision of leveraging data science and learning to address the difficult system problems in clouds for even lower cost and better availability. This talk will presents two recent projects: (1) CherryPick, which uses one active learning technique, Bayesian Optimization, to find the best cloud configurations for various big-data applications; (2) Vigil, which leverages TCP states collected from end hosts to diagnosis in-network failures. Finally, this talk will give an overview of the "AI for System" wave in Microsoft Research.
Biography
Hongqiang "Harry" Liu is a Researcher in Microsoft Research, Redmond Lab. He received his Ph.D. degree from the Department of Computer Science at Yale University in 2014, and his advisor is Prof. David Gelernter. Before joining Yale, he received his Master's and Bachelor's degrees from the Department of Electronic Engineering, Tsinghua University, Beijing. His research interest lies on many fields of networking and cloud computing, including software-defined networking (SDN), network function virtualization (NFV), and content delivery networks (CDN), edge computing, and network technologies for BigData, Linux container and virtual reality. Dr. Liu has published a number of papers in top-tier academic conferences, such as ACM SIGCOMM, USENIX NSDI and USENIX ATC. He is a recipient of the prestigious ACM SIGCOMM Doctoral Dissertation Award - Honorable Mention (2015) and Cascadia Innovation Fellowship (2011).