Concurrent Density Estimation with Wasserstein Autoencoders: Some Statistical Insights

• URL: http://arxiv.org/abs/2312.06591v1
• Date: Mon, 11 Dec 2023 18:27:25 GMT
• Title: Concurrent Density Estimation with Wasserstein Autoencoders: Some Statistical Insights
• Authors: Anish Chakrabarty, Arkaprabha Basu, Swagatam Das
• Abstract summary: Wasserstein Autoencoders (WAEs) have been a pioneering force in the realm of deep generative models. Our work is an attempt to offer a theoretical understanding of the machinery behind WAEs.
• Score: 20.894503281724052
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Variational Autoencoders (VAEs) have been a pioneering force in the realm of deep generative models. Amongst its legions of progenies, Wasserstein Autoencoders (WAEs) stand out in particular due to the dual offering of heightened generative quality and a strong theoretical backbone. WAEs consist of an encoding and a decoding network forming a bottleneck with the prime objective of generating new samples resembling the ones it was catered to. In the process, they aim to achieve a target latent representation of the encoded data. Our work is an attempt to offer a theoretical understanding of the machinery behind WAEs. From a statistical viewpoint, we pose the problem as concurrent density estimation tasks based on neural network-induced transformations. This allows us to establish deterministic upper bounds on the realized errors WAEs commit. We also analyze the propagation of these stochastic errors in the presence of adversaries. As a result, both the large sample properties of the reconstructed distribution and the resilience of WAE models are explored.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.