My research interests lie in the fields of machine learning and Bayesian
statistics. Specifically, I develop new methods and models to discover latent
structure in data, including cluster structure, using Bayesian nonparametrics,
hierarchical Bayes, techniques for Bayesian model comparison, and other
Bayesian statistical methods. I also leverage computer science algorithms and
ideas to perform inference efficiently.
I apply these methods to problems in cognitive science, where I strive to model
human behavior, including human categorization, and human social interactions
in online environments. I have also applied methods that I have developed to
some problems in computational biology, information retrieval, computer
security and computer vision.
I am serving as a probabilistic models and methods area chair for
I have been awarded an NSF postdoctoral fellowship on "Bayesian Models of
Social Behavior using Online Resources"!
J.T. Abbott, K.A. Heller, Z. Ghahramani, and T.L. Griffiths "Testing a
Bayesian Measure of Representativeness Using a Large Image Database", To
Neural Information Processing Systems (NIPS 2011).
S. Williamson, C. Wang, K.A. Heller, and D.M. Blei "Nonparametric Mixed
Membership Models using the IBP Compound Dirichlet Process", In
K.L. Mengerson, C.P. Robert, and D.M. Titterington, editors, Mixture
Estimation and Applications. John Wiley and Sons, 2011.
K.A. Heller and Z. Ghahramani, "Bayesian Hierarchical Clustering" In the Twenty-second International Conference on Machine Learning (ICML 2005). There is also a longer version, Gatsby Unit Technical Report GCNU-TR 2005-002. [ps] [pdf]