Do not falter or shrink; But just think out your work, And just work out your think. -- Nixon Waterman --

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.

In spring of 2008, I presented a thesis proposal on the theoretical foundations of active learning. Those interested can download it here [pdf][ps][slides], though it is a bit outdated already.

Publications:

I have begun several specific projects related to these interests, some of which have yielded publishable results.  Here are the papers I’ve published so far (authors are listed in alphabetical order).

2008

Balcan, M.-F., Hanneke, S., Wortman, J. (2008). The True Sample Complexity of Active Learning. In proceedings of the 21^st Annual Conference on Learning Theory (COLT). [pdf][ps][slides][slide show]
Winner of the Mark Fulk Best Student Paper Award.

2007

Balcan, M.-F., Even-Dar, E., Hanneke, S., Kearns, M., Mansour, Y., Wortman, J. (2007). Asymptotic Active Learning. NIPS Workshop on Principles of Learning Problem Design. [pdf][ps] [spotlight slide]

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 20^th 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 24^th 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 24^th Annual International Conference on Machine Learning (ICML). [pdf]
Also see our related earlier work.

Hanneke, S. (2007). The Complexity of Interactive Machine Learning. KDD Project Report (aka Master's Thesis). Machine Learning Department, Carnegie Mellon University. [pdf] [ps] [slides ppt]
Includes some interesting results from a class project on The Cost Complexity of Interactive Learning, in addition to my COLT07 and ICML07 papers.

2006

Hanneke, S. (2006). An Analysis of Graph Cut Size for Transductive Learning. In proceedings of the 23^rd International Conference on Machine Learning (ICML). [pdf][ps][slides ppt][slides pdf]

Hanneke, S. and Xing, E.P. (2006). Discrete Temporal Models of Social Networks. In proceedings of the ICML Workshop on Statistical Network Analysis. [pdf][ps]