Dimitris Margaritis
Assistant Professor

Office: 103 Atanasoff Phone: (515) 294-8052 Fax: (515) 294-0258 Email: dmarg@cs.iastate.edu Homepage: http://www.cs.iastate.edu/~dmarg/

Current Affiliations

• Department of Computer Science

Research Interests

I am interested in the theoretical and practical development of advanced algorithms for eliciting probabilistic models from data. In particular, I am interested in the learning of the structure of these models from data. I would like to use these algorithms in a variety of applications in bioinformatics, econometrics, database retrieval and many others.

Research Areas

Artificial Intelligence, Intelligent Agents and Multiagent Systems, Machine Learning and Data Mining, Bioinformatics and Computational Biology

Education

Ph.D.   Computer Science, Carnegie-Mellon University   2003
M.S.   Computer Science, SUNY at Stony Brook   1995
B.S.   Physics, University of Athens, Athens, Greece   1991

Honors and Awards

U.S. patent 6,584,221; Co-inventors: Baback Moghaddam (Mitsubishi Electric Research Lab, Cambridge, MA) and Henning Biermann (New York University)  "U.S. patent 6,584,221: Method for Image Retrieval with Multiple Regions of Interest", U.S. Patent Office, 2003

Representative Publications

Refereed Journal and Conference Publications

Facundo Bromberg, Dimitris Margaritis. Efficient and Robust Independence-Based Markov Network Discovery. International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, 2007.

Facundo Bromberg, Dimitris Margaritis and Vasant Honavar. Efficient Markov Network Structure Discovery from Independence Tests. SIAM International Conference on Data Mining (SDM), Bethesda, MD, Accepted, 2006.

Dimitris Margaritis. Distribution-Free Learning of Bayesian Network Structure in Continuous Domains. National Conference on Artificial Intelligence (AAAI), Pittsburgh, PA, AAAI Press / The MIT Press, 2005.

D. Margaritis, C. Faloutsos and S. Thrun. NetCube: A Scalable Tool for Fast Data Mining and Compression. 27th Conference on Very Large Databases (VLDB), Rome, Italy, 2001.

D. Margaritis and S. Thrun. A Bayesian Multiresolution Independence Test for Continuous Variables. 17th Conference on Uncertainty in Artificial Intelligence (UAI), Seattle, WA, 2001.

D. Margaritis and S. Thrun. Bayesian Network Induction via Local Neighborhoods. Advances in Neural Information Processing Systems 12 (NIPS), Denver, CO, 1999.