cid 8b7b7f887da9a3ee7a69c89d2910e4176292ee3223092d24966fc3e036d1b7eb · original · via openalex
Title: Local distance preservation in the GP-LVM through back constraints Authors: Neil David Lawrence; Joaquin Quiñonero-Candela Venue: International Conference on Machine Learning Year: 2006 Canonical: doi:10.1145/1143844.1143909 URL: https://doi.org/10.1145/1143844.1143909 Collector: openalex OA: false ABSTRACT The Gaussian process latent variable model (GP-LVM) is a generative approach to nonlinear low dimensional embedding, that provides a smooth probabilistic mapping from latent to data space. It is also a non-linear generalization of probabilistic PCA (PPCA) (Tipping & Bishop, 1999). While most approaches to non-linear dimensionality methods focus on preserving local distances in data space, the GP-LVM focusses on exactly the opposite. Being a smooth mapping from latent to data space, it focusses on keeping things apart in latent space that are far apart in data space. In this paper we first provide an overview of dimensionality reduction techniques, placing the emphasis on the kind of distance relation preserved. We then show how the GP-LVM can be generalized, through back constraints, to additionally preserve local distances. We give illustrative experiments on common data sets.