Bregman divergence as general framework to estimate unnormalized statistical models
Michael Gutmann, Jun-ichiro Hirayama
We show that the Bregman divergence provides a rich framework to estimate unnormalized statistical models for continuous or discrete random variables, that is, models which do not integrate or sum to one, respectively. We prove that recent estimation methods such as noise-contrastive estimation, ratio matching, and score matching belong to the proposed framework, and explain their interconnection based on supervised learning. Further, we discuss the role of boosting in unsupervised learning.
PDF Link: /papers/11/p283-gutmann.pdf
AUTHOR = "Michael Gutmann
and Jun-ichiro Hirayama",
TITLE = "Bregman divergence as general framework to estimate unnormalized statistical models",
BOOKTITLE = "Proceedings of the Twenty-Seventh Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-11)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2011",
PAGES = "283--290"