文档介绍：Acknowledgements
This thesis contains work that I did during the years 2001-2004 at Carnegie Mellon University.
Riemannian Geometry and Statistical Machine Learning During that period I received a lot of help from faculty, students and friends. However, I feel that
I should start by thanking my family: Alex, Anat and Eran Lebanon, for their support during
my time at Technion and Carnegie Mellon. Similarly, I thank Alfred Bruckstein, Ran El-Yaniv,
Michael Lindenbaum and Hava Siegelmann from the Technion for helping me getting started with
Doctoral Thesis
research puter science.
At Carnegie Mellon University I received help from a number of people, most importantly my
Guy Lebanon advisor John Lafferty. John helped me in many ways. He provided excellent technical hands-on
assistance, as well as help on high-level and strategic issues. Working with John was a very pleasant
Language Technologies Institute
and educational experience. It fundamentally changed the way I do research and turned me into
School puter Science
a better researcher. I also thank John for providing an excellent environment for research without
Carnegie Mellon University
distractions and for making himself available whenever I needed.
******@
January 31, 2005 I thank my mittee members Geoffrey J. Gordon, Michael I. Jordan and Larry Wasser-
man for their ments. I benefited from interactions with several graduate students at
Carnegie Mellon University. Risi Kondor, Leonid Kontorovich, Luo Si, Jian Zhang and Xioajin Zhu
provided ments on different parts of the thesis. Despite not helping directly on topics
related to the thesis, I benefited from interactions with Chris Meek at Microsoft Research, Yoram
Singer at the Hebrew University and Joe i and Douglas Critchlow at Ohio State University.
These interactions improved my understanding of machine learning and helped me write a better
thesis.
Abstract
Statistical machine learning algorithms deal