← Search

Nishith Khandwala

1 accepted papers

2017

Inferring Generative Model Structure with Static Analysis

NeurIPS 2017poster

Obtaining enough labeled data to robustly train complex discriminative models is a major bottleneck in the machine learning pipeline. A popular solution is combining multiple sources of weak supervision using generative models. The structure of these models affects the quality of the training labels…

Cited by 69SourcePDFScholar