Feature Selection and Dualities in Maximum Entropy Discrimination
Tony Jebara, Tommi Jaakkola
Incorporating feature selection into a classification or regression method often carries a number of advantages. In this paper we formalize feature selection specifically from a discriminative perspective of improving classification/regression accuracy. The feature selection method is developed as an extension to the recently proposed maximum entropy discrimination (MED) framework. We describe MED as a flexible (Bayesian) regularization approach that subsumes, e.g., support vector classification, regression and exponential family models. For brevity, we restrict ourselves primarily to feature selection in the context of linear classification/regression methods and demonstrate that the proposed approach indeed carries substantial improvements in practice. Moreover, we discuss and develop various extensions of feature selection, including the problem of dealing with example specific but unobserved degrees of freedom -- alignments or invariants.
Keywords: Feature Selection, Regression, Classification, Discrimination, Maximum Entropy, Suppo
PS Link: http://www.media.mit.edu/~jebara/med/uai.ps
PDF Link: /papers/00/p291-jebara.pdf
AUTHOR = "Tony Jebara
and Tommi Jaakkola",
TITLE = "Feature Selection and Dualities in Maximum Entropy Discrimination",
BOOKTITLE = "Proceedings of the Sixteenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-00)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "2000",
PAGES = "291--300"