Distributed machine learning problems for big graphs

Prof. Alex Dimakis
University of Texas - Austin

Abstract:
Many datasets from the web, social networks, bioinformatics and neuroscience are naturally graph-structured. Graph algorithms are difficult to implement in distributed computation frameworks like Hadoop MapReduce and for this reason several in-memory graph engines like Pregel, GraphLab and GraphX are being currently developed. Our goal is to design parallelizable algorithms that discover graph structural properties and theoretically analyze their performance. We give an overview of the emerging problems in designing distributed algorithms over such graph engines and discuss future directions.

Bio:
Alex Dimakis is an Assistant Professor at the Electrical and Computer Engineering department, UT Austin. From 2009 until 2012 he was with USC. He received his Ph.D. in 2008 in electrical engineering and computer sciences from UC Berkeley and the Diploma degree from the National Technical University of Athens in 2003. During 2009 he was a CMI postdoctoral scholar at Caltech.
He received an NSF Career award in 2011, a Google faculty research award in 2012 and the Eli Jury dissertation award in 2008. He is the co-recipient of several best paper awards including the joint Information Theory and Communications Society Best Paper Award in 2012.
His research interests include information theory, signal processing, and networking, with a current focus on distributed storage and machine learning.