Dan Geiger
no text seen here - or change color
  • Professor of Computer Science, Technion - Israel Institute of Technology
  • Head of the Computational Biology Laboratory
Research Interests
My main research is focused on the study of probabilistic models for intelligent systems, in particular, the study of Bayesian networks and their applications in Bioinformatics and in other domains. I have focused my attention on several aspects of Bayesian networks, including, (1) Foundation - which independence assumptions are encoded in a Bayesian network, (2) Exact Inference - how to efficiently answer queries using a Bayesian network, (3) Learning - how to learn Bayesian networks from data, and (4) Applications - building effective intelligent systems based on Bayesian networks. Currently, I am mostly interested in using probabilistic models effectively for mapping disease genes and for other Bioinformatics tasks. I am interested in building state of the art software packages that help geneticists map genes for complex diseases either by linkage studies, association studies, or other methods. The experience with graphical models has lead me to construct with my students an efficient program for linkage analysis called Superlink to which I devote a sizeable portion of my time.
Ph.D Students
  • Anna Becker. Graduated 2000. Studied combinatorial problems related to exact inference and their applications to genetic linkage analysis.
  • Ma'ayan Fishelson. Graduated 2004. Studied genetic linkage analysis.
  • Dmitry Rusakov. Graduated 2004. Studied asymptotic Bayesian model selection criteria.
  • Gideon Greenspan. Graduated 2005. Studied blocks of SNPs and their usage in association analysis.
  • Ydo Wexler. Studies approximate inference with applications to genetic linkage analysis.
  • Ron Zohar. Studies group tracking methodologies using probabilistic models.
Journal Publications

  •   Judea Pearl, Dan Geiger, and Tom Verma. Conditional independence and its representations. Kybernetica, 25 (1989) 33--44.

  •   Dan Geiger, Tom Verma and Judea Pearl. Identifying independence in Bayesian networks. Networks, 20 (1990) 507--534.

  •   Dan Geiger and Judea Pearl. Logical and algorithmic properties of independence and their application to Bayesian networks. Annals of Mathematics and Artificial Intelligence, 2 (1990) 165--178.

  •   Dan Geiger, Azaria Paz, and Judea Pearl. Axioms and algorithms for inferences involving probabilistic Independence. Information and Computation 1 (1991) 128--141.

  •   Dan Geiger, Azaria Paz, and Judea Pearl. Learning simple causal structures. International Journal of Intelligent Systems, 8 (1993) 231--247.

  •   Dan Geiger and Judea Pearl. Logical and algorithmic properties of conditional independence and graphical models. Annals of Statistics, 21 (1993), 2001--2021.

  •   D. Chickering, D. Geiger, and D. Heckerman. On finding a cycle basis with a shortest maximal cycle. Information Processing Letters 54 (1995) 55--58.

  •   Amir Eliaz and Dan Geiger, Word-level recognition of small sets of hand written words. Pattern Recognition Letters, 1995, 16 (10), 999--1009.

  •   David Heckerman, Dan Geiger, and David M. Chickering, Learning Bayesian networks: The combination of knowledge and statistical data. Machine Learning, 1995, 20(3), 197--243.

  •   Dan Geiger and David Heckerman. Knowledge representation and inference in similarity networks and Bayesian multinets. Artificial Intelligence Journal 82 (1996), 1--30.

  •   Ann Becker and Dan Geiger. Optimization of Pearl's method of conditioning and greedy-like approximation algorithms for the vertex feedback set problem. Artificial Intelligence Journal 83 (1996), 1--22.

  •   Dan Geiger and Eyal Zussman. Probabilistic reactive disassembly planning. Annals of the CIRPS, 45 (1996). (A publication of Mechanical Engineering).

  •   Dan Geiger and David Heckerman. A characterization of the Dirichlet distribution through global and local parameter independence. Annals of Statistics, 25(3), 1997.

  •   Nir Friedman, Dan Geiger, and Moises Goldszmidt. Building classifiers using Bayesian networks. Machine Learning, 29, 131--163, 1997

  •   Reuven Bar-Yehuda, Dan Geiger, Seffi Naor, and Ron Roth. Approximation algorithms for the feedback vertex set problem with applications to constraint satisfaction and Bayesian inference, SIAM Journal of Computing, 27(4), 942--959, 1998.

  •   Dan Geiger and David Heckerman. Probabilistic relevance relations, IEEE Systems Man and Cybernetics, 28(1), 1998.

  •   Dan Geiger and David Heckerman. A characterization of the bivariate Wishart distribution, Probability and Mathematical Statistics, 18(1), 119--131, 1998. 1998.

  •   Ann Becker, Dan Geiger, Alejandro Schäffer, Automatic selection of loop breakers for genetic linkage analysis. Human Genetics, 48(1), 49--60, 1998.

  •   Ann Becker, Reuven Bar-Yehuda, and Dan Geiger. Randomized algorithms for the loop cutset problem. Journal Artificial Intelligence Research, 12 (2000), 219--234.

  •   Ann Becker and Dan Geiger. A sufficiently fast algorithm for finding close to optimal clique trees. Artificial Intelligence Journal, 125 (2001), 3--17.

  •   Dan Geiger, David Heckerman, Henry King, and Christopher Meek. Stratified exponential families: Graphical models and model selection. Annals of Statistics, 29 (2001), 505--529.

  •   Dan Geiger and David Heckerman. Parameter priors for directed acyclic graphs and the characterization of several probability distributions. Annals of Statistics, 30 (2002), 1412--1440.

  •   Ma'ayan Fishelson and Dan Geiger. Exact Genetic Linkage Computations for General Pedigrees. Bioinformatics, 18 (2002), S189--S198.

  •   Gideon Greenspan, Dan Geiger, F. Gotch, M. Bower, S. Patterson, M. Nelson, B. Gazzard and J. Stebbing. Model-based inference of recombination hotspots in a highly variable oncogene. Journal of Molecular Evolution, 58 (2004), 239--251.

  •   Ma'ayan Fishelson and Dan Geiger. Optimizing exact genetic linkage computations. Journal of Computational Biology, 11 (2004).

  •   Gideon Greenspan and Dan Geiger. Model-based inference of haplotype block variation. Journal of Computational Biology, 11 (2004).

  •   Dmitry Rusakov and Dan Geiger. Asymptotic Model Selection for Naive Bayesian Networks. Journal of Machine Learning Reseach, (2004).

  •   Ginat Narkis, Daniella Landau, Esther Manor, Khalil Elbedour, Anna Tzemach, Ma'ayan Fishelson, Dan Geiger, Rivka Carmi, Rivka Ofir, Ohad S. Birk. Homozygosity mapping of lethal congenital contractural syndrome type 2 (LCCS2) to a 6 cM interval on chromosome 12q13. American Journal of Medical Genetics, (2004).

  •   Gideon Greenspan and Dan Geiger. High density linkage disequilibrium mapping using models of haplotype block variation. Bioinformatics, (2004).

  •   Vladimir Jojic, Nebojsa Jojic, Chris Meek, Dan Geiger, Adam Siepel, David Haussler, and David Heckerman. Efficient approximations for learning phylogenetic HMM models from data. Bioinformatics, (2004).
    • Software
    Contact Information
    Electronic mail: dang@cs.technion.ac.il
    Office phone number: +972 4 829 4339
    Address: Technion - Israel Institute of Technology, Computer Science Department, Taub 616, Haifa, 36000, Israel
    Link to the Laboratory of Computational Biology