A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Approximated Geodesic Updates with Principal Natural Gradients
2007
Neural Networks (IJCNN), International Joint Conference on
We propose a novel optimization algorithm which overcomes two drawbacks of Amari's natural gradient updates for information geometry. First, prewhitening the tangent vectors locally converts a Riemannian manifold to an Euclidean space so that the additive parameter update sequence approximates geodesics. Second, we prove that dimensionality reduction of natural gradients is necessary for learning multidimensional linear transformations. Removal of minor components also leads to noise reduction
doi:10.1109/ijcnn.2007.4371149
dblp:conf/ijcnn/YangL07
fatcat:r6bbfwsz7zcixac5fzzefm3kxu