When: Monday, May 05, 1:30 p.m.

Where: 3305Newell-Simon Hall

Mino Garafalakis, Principal Research Scientist
Yahoo! Research

Seminar

Abstract:
Most natural data-stream management scenarios arise in large-scale event monitoring applications; for instance, network-operations monitoring in large ISPs, where usage information from numerous sites needs to be continuously collected and analyzed for potential anomalies or interesting trends. In addition to the traditional data-streaming concerns of memory/time efficiency, the inherently distributed nature of such applications also raises important communication-efficiency issues, making it critical to carefully optimize the use of the underlying network infrastructure. Intuitive in-network processing ideas, like "filtering at the edge" and "sharing simple prediction models", turn out to be quite powerful in this context, often resulting in dramatic improvements in communication efficiency for different distributed streaming problems. In this talk, we introduce the distributed data streaming model, and discuss our recent results on tracking complex queries and traffic-volume anomalies over distributed streams, as well as new research directions in this space.

Minos Garofalakis is a Principal Research Scientist with the Community Systems group at Yahoo! Research in Santa Clara, California, and an Adjunct Associate Professor of Computer Science at the University of California, Berkeley. Previously, he was a Senior Researcher at Intel Research Berkeley (2005-2007), and a Member of Technical Staff at Bell Laboratories (1998-2005). He obtained his PhD from the University of Wisconsin-Madison in 1998. Minos currently serves as an Associate Editor for ACM Transactions on Database Systems (ACM TODS) and IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), and as an Editorial Board Member for Foundations and Trends in Databases; he also recently served as the Core Database Technology PC Chair for the VLDB'2007 conference in Vienna, Austria, and completed a term as an Associate Editor for the IEEE Data Engineering Bulletin (2004-2006). Minos' current research interests include data streaming, approximate query processing, probabilistic databases, network-data management, and XML databases.

<< Back