11
28

Learning about an exponential amount of conditional distributions

Abstract

We introduce the Neural Conditioner (NC), a self-supervised machine able to learn about all the conditional distributions of a random vector XX. The NC is a function NC(xa,a,r)NC(x \cdot a, a, r) that leverages adversarial training to match each conditional distribution P(XrXa=xa)P(X_r|X_a=x_a). After training, the NC generalizes to sample from 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.

View on arXiv
Comments on this paper