pith. sign in

arxiv: 1902.08401 · v1 · pith:CCEBL5LHnew · submitted 2019-02-22 · 💻 cs.LG · stat.ML

Learning about an exponential amount of conditional distributions

classification 💻 cs.LG stat.ML
keywords conditionaldistributiondistributionsabledatalearningself-supervisedtasks
0
0 comments X
read the original 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 $NC(x \cdot a, a, r)$ that leverages adversarial training to match each conditional distribution $P(X_r|X_a=x_a)$. 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.