The Generative and Discriminative Learning Interface

Generative and discriminative learning are two of the major paradigms for solving prediction problems in machine learning, each offering important distinct advantages. They have often been studied in different sub-communities, but over the past decade, there has been increasing interest in trying to understand and leverage the advantages of both approaches. The goal of this workshop is to map out our current understanding of the empirical and theoretical advantages of each approach as well as their combination, and to identify open research directions.