Adversarial Jamming for Autoencoder Distribution Matching
This provides a novel method for distribution matching in autoencoders, which is incremental as it builds on existing adversarial jamming concepts.
The paper tackles the problem of matching the latent space distribution of an autoencoder to a diagonal Gaussian by using adversarial wireless jamming as a regularization technique, achieving results comparable to standard variational and Wasserstein autoencoders.
We propose the use of adversarial wireless jamming to regularise the latent space of an autoencoder to match a diagonal Gaussian distribution. We consider the minimisation of a mean squared error distortion, where a jammer attempts to disrupt the recovery of a Gaussian source encoded and transmitted over the adversarial channel. A straightforward consequence of existing theoretical results is the fact that the saddle point of a minimax game - involving such an encoder, its corresponding decoder, and an adversarial jammer - consists of diagonal Gaussian noise output by the jammer. We use this result as inspiration for a novel approach to distribution matching in the latent space, utilising jamming as an auxiliary objective to encourage the aggregated latent posterior to match a diagonal Gaussian distribution. Using this new technique, we achieve distribution matching comparable to standard variational autoencoders and to Wasserstein autoencoders. This approach can also be generalised to other latent distributions.