Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders This post is a work through for this paper by Natasa et al: Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders, one can find the paper here . Introduction The authors introduced vine copula autoencoder (VCAE) as a flexible generative model for high-dimensional distributions. The model is simply built in a three-step procedure: Train an autoencoder to compress the data into a lower dimensional representations; Estimate the encoded representation's distribution with vine copulas; Combine the distribution and the decoder to generate new data points. The authors claimed that this generative model has 3 advantages compared to Generative Adversarial Nets (GANs) and Variational Autoencoders (VAEs): It offers modeling flexibility by avoiding most distributional assumptions in contrast to VAEs; Training and sampling procedures for high-dimensional data are straightforward; It can be used...