Learning Nonparametric High-Dimensional Generative Models: The Empirical-Beta-Copula Autoencoder
This addresses the challenge of generating high-dimensional data from autoencoders for researchers in machine learning, but it is incremental as it builds on existing copula and autoencoder approaches.
The study tackled the problem of turning autoencoders into generative models by modeling their latent space distributions, comparing various techniques and introducing the Empirical Beta Copula Autoencoder as a new method.
By sampling from the latent space of an autoencoder and decoding the latent space samples to the original data space, any autoencoder can simply be turned into a generative model. For this to work, it is necessary to model the autoencoder's latent space with a distribution from which samples can be obtained. Several simple possibilities (kernel density estimates, Gaussian distribution) and more sophisticated ones (Gaussian mixture models, copula models, normalization flows) can be thought of and have been tried recently. This study aims to discuss, assess, and compare various techniques that can be used to capture the latent space so that an autoencoder can become a generative model while striving for simplicity. Among them, a new copula-based method, the Empirical Beta Copula Autoencoder, is considered. Furthermore, we provide insights into further aspects of these methods, such as targeted sampling or synthesizing new data with specific features.