Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders

Abstract

We introduce the vine copula autoencoder (VCAE), a flexible generative model for high-dimensional distributions built in a straightforward three-step procedure. First, an autoencoder (AE) compresses the data into a lower dimensional representation. Second, the multivariate distribution of the encoded data is estimated with vine copulas. Third, a generative model is obtained by combining the estimated distribution with the decoder part of the AE. As such, the proposed approach can transform any already trained AE into a flexible generative model at a low computational cost. This is an advantage over existing generative models such as adversarial networks and variational AEs which can be difficult to train and can impose strong assumptions on the latent space. Experiments on MNIST, Street View House Numbers and Large-Scale CelebFaces Attributes datasets show that VCAEs can achieve competitive results to standard baselines.

References in corpus (10)

• Auto-Encoding Variational Bayes
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Variational Inference with Normalizing Flows
• Unrolled Generative Adversarial Networks
• Evading the curse of dimensionality in nonparametric density estimation with simplified vine copulas
• AdaGAN: Boosting Generative Models
• Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations
• Revisiting Classifier Two-Sample Tests
• From Dependence to Causation

Cited by in corpus (4)

• Distinguishing Cause from Effect Using Quantiles: Bivariate Quantile Causal Discovery
• Effect of backdoor attacks over the complexity of the latent space distribution
• Implicit Generative Copulas
• Generative Archimedean Copulas