Informatics, TU Vienna

There and Back Again

Outlier Detection between Statistical Reasoning and Efficient Database Methods.


While classical statistical methods for outlier detection had a focus on probabilistic reasoning, research on outlier detection in the database context during the last decade focused on the development of ever more efficient methods to compute outlier scores without much reasoning about the meaning of these scores. In this talk, we sketch this development and introduce some methods that go back again to statistical reasoning on top of the efficient database techniques. As we demonstrate, this opens up new possibilities for the design of ensemble methods for outlier detection.


Dr. Arthur Zimek is a Privatdozent in the database systems and data mining group of Hans-Peter Kriegel at the Ludwig-Maximilians-Universität München, Germany. 2012--2013 he was a postdoctoral fellow in the department for Computing Science at the University of Alberta, Edmonton, Canada. He finished his Ph.D. thesis in informatics on "Correlation Clustering" in summer 2008, and received for this work the "SIGKDD Doctoral Dissertation Award (runner-up)" in 2009. Together with his co-authors, he received the "Best Paper Honorable Mention Award" at SDM 2008 and the "Best Demonstration Paper Award" at SSTD 2011. Zimek has served in program committees (e.g. SIGKDD, ECMLPKDD, CIKM) and as reviewer for journals like ACM TKDD, IEEE TKDE, Data Min.~Knowl.~Disc., Machine Learning etc.


This talk is organized by the Vienna PhD School of Informatics and part of the lecture series "Current Trends in Computer Science".