Sciweavers

UAI
2004

An Extended Cencov-Campbell Characterization of Conditional Information Geometry

14 years 10 days ago
An Extended Cencov-Campbell Characterization of Conditional Information Geometry
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.
Guy Lebanon
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where UAI
Authors Guy Lebanon
Comments (0)