Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings   Proceeding details   Article details         Authors         Search    
An Extended Cencov-Campbell Characterization of Conditional Information Geometry
Guy Lebanon
We formulate and prove an axiomatic characterization of conditional information geometry, for both the normalized and the nonnormalized cases. This characterization extends the axiomatic derivation of the Fisher geometry by Cencov and Campbell to the cone of positive conditional models, and as a special case to the manifold of conditional distributions. Due to the close connection between the conditional I-divergence and the product Fisher information metric the characterization provides a new axiomatic interpretation of the primal problems underlying logistic regression and AdaBoost.
Keywords: null
Pages: 341-348
PS Link:
PDF Link: /papers/04/p341-lebanon.pdf
AUTHOR = "Guy Lebanon ",
TITLE = "An Extended Cencov-Campbell Characterization of Conditional Information Geometry",
BOOKTITLE = "Proceedings of the Twentieth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-04)",
ADDRESS = "Arlington, Virginia",
YEAR = "2004",
PAGES = "341--348"

hosted by DSL   •   site info   •   help