Distributional Principal Autoencoders

arXiv:2404.13649v1 Announce Type: cross
Abstract: Dimension reduction techniques usually lose information in the sense that reconstructed data are not identical to the original data. However, we argue that it is possible to have reconstructed data identically distributed as the original data, irrespective of the retained dimension or the specific mapping. This can be achieved by learning a distributional model that matches the conditional distribution of data given its low-dimensional latent variables. Motivated by this, we propose Distributional Principal Autoencoder (DPA) …

abstract arxiv autoencoders cs.lg data distributed however information mapping sense stat.me stat.ml type