Do not falter or shrink; But just think out your work, And just work out your think. -- Nixon Waterman --
Note: THIS WEBSITE IS OUT-DATED. I have now moved to a Visiting Assistant Professor position in the Department of Statistics at Carnegie Mellon University. My new webpage is http://www.stat.cmu.edu/~shanneke/. You should be automatically forwarded, or you can manually go there by clicking here.
My general research interest is in artificial intelligence; specifically, I am interested in systems that can improve their performance with experience, a problem known as machine learning.
My focus is on the informational complexity of machine learning. The essential questions I am interested in answering are "what can be learned from empirical observation and/or interaction," and "how much observation and/or interaction is necessary to learn it?" This overall topic intersects with several academic disciplines, including statistical inference, learning theory, algorithmic and statistical information theories, philosophy of science, and epistemology.
I also do some work on statistical modeling of social networks.
I also have some ``working notes'' that may be of interest to some people. These include unpublished results, which will eventually make it into my thesis, and possibly other publications in some cases. These notes are subject to frequent updates and changes -- mostly additions -- as I continue to explore these topics.
Rates of Convergence in Active Learning. (includes a survey of recent advances in studying rates of convergence in agnostic active learning, along with some new results).
A Refined Analysis of PAC Learning Via the Disagreement Coefficient. (the disagreement coefficient turns out to be useful for studying passive learning too).
Publications: (authors are listed in alphabetical order).
Balcan, M.-F., Hanneke, S., Wortman, J. (2008).
The True Sample Complexity of Active Learning.
In proceedings of the 21st Annual Conference on Learning Theory (COLT).
Hanneke, S., and Xing, E.P. (2007). Network Completion and Survey Sampling. NIPS Workshop on Statistical Network Models.
Hanneke, S. (2007). Teaching Dimension and the Complexity of Active Learning. In proceedings of the 20th Annual Conference on Learning Theory (COLT). [pdf][ps][slides ppt]
Hanneke, S. (2007). A Bound on the Label Complexity of Agnostic Active Learning. In proceedings of the 24th Annual International Conference on Machine Learning (ICML). [pdf][ps][slides ppt]
Fu, W., Guo, F., Hanneke, S., and Xing, E.P. (2007).
Recovering Temporally Rewiring Networks:
A Model-based Approach.
In proceedings of the 24th Annual International Conference on
Machine Learning (ICML). [pdf]
Hanneke, S. (2007).
The Complexity of Interactive Machine Learning.
KDD Project Report (aka Master's Thesis).
Machine Learning Department, Carnegie Mellon University.
Hanneke, S. (2006). An Analysis of Graph Cut Size for Transductive Learning. In proceedings of the 23rd International Conference on Machine Learning (ICML). [pdf][ps][slides ppt][slides pdf]10/24/09 - Present