Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
This provides a simpler and more computationally efficient alternative to complex generative models like GANs and VAEs for researchers and practitioners in machine learning, though it is incremental as it builds on existing autoencoder and copula methods.
The paper tackles the challenge of creating flexible generative models for high-dimensional data by introducing the vine copula autoencoder (VCAE), which transforms any trained autoencoder into a generative model using vine copulas, achieving competitive results on datasets like MNIST, SVHN, and CelebFaces.
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.