Timezone: »

 
Poster
Learning about an exponential amount of conditional distributions
Mohamed Ishmael Belghazi · Maxime Oquab · David Lopez-Paz

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #69
in Algorithms -- Unsupervised Learning »

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⋅a,a,r) that leverages adversarial training to match each conditional distribution P(Xr|Xa=xa). 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.

Keywords: Unsupervised Learning · Representation Learning · Algorithms
[ Paper]  [ Poster] 

Author Information

Mohamed Ishmael Belghazi (MILA)
Maxime Oquab (Facebook AI Research)
David Lopez-Paz (Facebook AI Research)

More from the Same Authors