A Bayesian Non-parametric Approach to Generative Models: Integrating Variational Autoencoder and Generative Adversarial Networks using Wasserstein and Maximum Mean Discrepancy
This addresses generative modeling challenges for researchers and practitioners, offering a novel integration that improves sample quality and diversity, though it appears incremental as it builds on existing GAN and VAE frameworks.
The paper tackles failure modes in GANs and VAEs, such as overfitting and noisy samples, by proposing a Bayesian non-parametric generative model that integrates these methods with Wasserstein and maximum mean discrepancy, achieving enhanced training stability and superior performance on various datasets.
We propose a novel generative model within the Bayesian non-parametric learning (BNPL) framework to address some notable failure modes in generative adversarial networks (GANs) and variational autoencoders (VAEs)--these being overfitting in the GAN case and noisy samples in the VAE case. We will demonstrate that the BNPL framework enhances training stability and provides robustness and accuracy guarantees when incorporating the Wasserstein distance and maximum mean discrepancy measure (WMMD) into our model's loss function. Moreover, we introduce a so-called ``triple model'' that combines the GAN, the VAE, and further incorporates a code-GAN (CGAN) to explore the latent space of the VAE. This triple model design generates high-quality, diverse samples, while the BNPL framework, leveraging the WMMD loss function, enhances training stability. Together, these components enable our model to achieve superior performance across various generative tasks. These claims are supported by both theoretical analyses and empirical validation on a wide variety of datasets.