Learning in Riemannian Orbifolds
Machine Learning
2012-04-20 v1 Artificial Intelligence
Computer Vision and Pattern Recognition
Abstract
Learning in Riemannian orbifolds is motivated by existing machine learning algorithms that directly operate on finite combinatorial structures such as point patterns, trees, and graphs. These methods, however, lack statistical justification. This contribution derives consistency results for learning problems in structured domains and thereby generalizes learning in vector spaces and manifolds.
Cite
@article{arxiv.1204.4294,
title = {Learning in Riemannian Orbifolds},
author = {Brijnesh J. Jain and Klaus Obermayer},
journal= {arXiv preprint arXiv:1204.4294},
year = {2012}
}
Comments
arXiv admin note: substantial text overlap with arXiv:1001.0921