Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)
Abstract
We introduce the Locally Linear Latent Variable Model (LL-LVM), a probabilistic model for non-linear manifold discovery that describes a joint distribution over observations, their manifold coordinates and locally linear maps conditioned on a set of neighbourhood relationships. The model allows straightforward variational optimisation of the posterior distribution on coordinates and locally linear maps from the latent space to the observation space given the data. Thus, the LL-LVM encapsulates the local-geometry preserving intuitions that underlie non-probabilistic methods such as locally linear embedding (LLE). Its probabilistic semantics make it easy to evaluate the quality of hypothesised neighbourhood relationships, select the intrinsic dimensionality of the manifold, construct out-of-sample extensions and to combine the manifold model with additional probabilistic models that capture the structure of coordinates within the manifold.
Cite
@article{arxiv.1410.6791,
title = {Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)},
author = {Mijung Park and Wittawat Jitkrittum and Ahmad Qamar and Zoltan Szabo and Lars Buesing and Maneesh Sahani},
journal= {arXiv preprint arXiv:1410.6791},
year = {2015}
}
Comments
accepted to NIPS 2015