Disentangling representations in Restricted Boltzmann Machines without adversaries. (arXiv:2206.11600v2 [cs.LG] UPDATED)

A goal of unsupervised machine learning is to disentangle representations of
complex high-dimensional data, allowing for interpreting the significant latent
factors of variation in the data as well as for manipulating them to generate
new data with desirable features. These methods often rely on an adversarial
scheme, in which representations are tuned to avoid discriminators from being
able to reconstruct specific data information (labels). We propose a simple,
effective way of disentangling representations without any need to train
adversarial discriminators, …

arxiv boltzmann lg machines