A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data

arXiv:2402.15710v1 Announce Type: new
Abstract: Variational Autoencoders (VAEs) have gained significant popularity among researchers as a powerful tool for understanding unknown distributions based on limited samples. This popularity stems partly from their impressive performance and partly from their ability to provide meaningful feature representations in the latent space. Wasserstein Autoencoders (WAEs), a variant of VAEs, aim to not only improve model efficiency but also interpretability. However, there has been limited focus on analyzing their statistical guarantees. The matter is further …

abstract analysis arxiv autoencoders cs.lg data feature low math.st performance researchers samples space statistical stat.ml stat.th tool type understanding variational autoencoders