Paraskevas (Paris) Yiapanis

PhD Student
Room number: IT-302
Homepage: www.cs.man.ac.uk/~a_n_other
Other contact details
email: pyiapanis@cs.manchester.ac.uk

I am a PhD student at the School Of Computer Science at the University of Manchester, UK. I have been with the Advanced Processor Technologies Group since September 2008, supervised by Mikel Lujan and Gavin Brown.
I hold a Master of Science in Software Engineering from the same University and a Bachelor of Science in Computer Science from Radford University, USA.

I am currently working on the iTLS (intelligent Thread-Level Speculation) project which brings together the areas of Machine Learning and Thread-Level Speculation to facilitate automatic run-time parallelization of sequential applications.

Research Interests:

• Automatic Parallelization
• Thread-Level Speculation
• Transactional Memory
• Back-end Compilers
• Parallel Architectures
• Itemset/Pattern Mining
• Association Rules
• Classification and Prediction algorithms

Publications:

• Adam Pocock, Paraskevas Yiapanis, Jeremy Singer, Mikel Luján, and Gavin Brown. "Online Nonstationary Boosting". To appear in Proceedings of the International Workshop on Multiple Classifier Systems. April 2010.
  [PDF]
• Jeremy Singer, Paraskevas Yiapanis, Adam Pocock, Mikel Luján, Gavin Brown, Nikolas Ioannou, and Marcelo Cintra. "Static Java Program Features for Intelligent Squash Prediction". In the 4th Workshop on Statistical and Machine learning approaches to ARchitecture and compilaTion (SMART'10), January 2010.
  [PDF]
• Paraskevas Yiapanis, Jeremy Singer, Adam Pocock, Mikel Luján, Gavin Brown. "Mining Static Features for Squash Prediction in Thread-Level Speculation". In the 5th International Summer School on Advanced Computer Architecture and Compilation for Embedded Systems (ACACES'09), July 2009.
  [PDF]
• Jeremy Singer, Gavin Brown, Mikel Luján, Adam Pocock and Paraskevas Yiapanis. "Fundamental Nano-Patterns to Characterize and Classify Java Methods". In Proceedings of the Workshop on Language Descriptions, Tools and Applications (LDTA), March 2009.
  [PDF]
• Paraskevas Yiapanis, David J. Haglin, Anna M. Manning, Ken Mayes, and John Keane, "Variable-grain and Dynamic Work Generation for Minimal Unique Itemset Mining", in 2008 IEEE International Conference on Cluster Computing (Cluster 2008), Tsukuba, Japan, 29 Sep - 1 Oct 2008, pp. 33-41.
  [PDF]
• Paraskevas Yiapanis. "Parallel Mining of Minimal Sample Unique Itemsets". MSc Thesis, School of Computer Science, The University of Manchester, 2007.
  [PDF]