Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings   Proceeding details   Article details         Authors         Search    
Bregman divergence as general framework to estimate unnormalized statistical models
Michael Gutmann, Jun-ichiro Hirayama
Abstract:
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.
Keywords:
Pages: 283-290
PS Link:
PDF Link: /papers/11/p283-gutmann.pdf
BibTex:
@INPROCEEDINGS{Gutmann11,
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"
}


hosted by DSL   •   site info   •   help