Abstract

We introduce the Neural Conditioner (NC), a self-supervised machine able to learn about all the conditional distributions of a random vector X. The NC is a function NC(xa, a, r) that leverages adversarial training to match each conditional distribution After training, the NC generalizes to sample conditional distributions never seen, including the joint distribution. The NC is also able to auto-encode examples, providing data representations useful for downstream classification tasks. In sum, the NC integrates different self-supervised tasks (each being the estimation of a conditional distribution) and levels of supervision (partially observed data) seamlessly into a single learning experience.