Doubly Stochastic Adversarial Autoencoder
This is an incremental improvement for generative modeling in machine learning, addressing limitations in existing adversarial methods.
The paper tackles the problem of generating diverse samples in autoencoder-based generative models by replacing the deterministic adversary in Adversarial Autoencoders with a stochastic function space, which prevents overfitting and enhances exploration, resulting in improved sample diversity.
Any autoencoder network can be turned into a generative model by imposing an arbitrary prior distribution on its hidden code vector. Variational Autoencoder (VAE) [2] uses a KL divergence penalty to impose the prior, whereas Adversarial Autoencoder (AAE) [1] uses {\it generative adversarial networks} GAN [3]. GAN trades the complexities of {\it sampling} algorithms with the complexities of {\it searching} Nash equilibrium in minimax games. Such minimax architectures get trained with the help of data examples and gradients flowing through a generator and an adversary. A straightforward modification of AAE is to replace the adversary with the maximum mean discrepancy (MMD) test [4-5]. This replacement leads to a new type of probabilistic autoencoder, which is also discussed in our paper. We propose a novel probabilistic autoencoder in which the adversary of AAE is replaced with a space of {\it stochastic} functions. This replacement introduces a new source of randomness, which can be considered as a continuous control for encouraging {\it explorations}. This prevents the adversary from fitting too closely to the generator and therefore leads to a more diverse set of generated samples.