Efficient Parametric Projection Pursuit Density Estimation
Machine Learning
2012-12-12 v1 Machine Learning
Abstract
Product models of low dimensional experts are a powerful way to avoid the curse of dimensionality. We present the ``under-complete product of experts' (UPoE), where each expert models a one dimensional projection of the data. The UPoE is fully tractable and may be interpreted as a parametric probabilistic model for projection pursuit. Its ML learning rules are identical to the approximate learning rules proposed before for under-complete ICA. We also derive an efficient sequential learning algorithm and discuss its relationship to projection pursuit density estimation and feature induction algorithms for additive random field models.
Cite
@article{arxiv.1212.2513,
title = {Efficient Parametric Projection Pursuit Density Estimation},
author = {Max Welling and Richard S. Zemel and Geoffrey E. Hinton},
journal= {arXiv preprint arXiv:1212.2513},
year = {2012}
}
Comments
Appears in Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence (UAI2003)