Poster
Bias and Generalization in Deep Generative Models: An Empirical Study
Shengjia Zhao · Hongyu Ren · Arianna Yuan · Jiaming Song · Noah Goodman · Stefano Ermon
Room 210 #6
Keywords: [ Visualization or Exposition Techniques for Deep Networks ] [ Visual Perception ] [ Latent Variable Models ] [ Generative Models ] [ Adversarial Networks ]
In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework to systematically investigate bias and generalization in deep generative models of images by probing the learning algorithm with carefully designed training datasets. By measuring properties of the learned distribution, we are able to find interesting patterns of generalization. We verify that these patterns are consistent across datasets, common models and architectures.
Live content is unavailable. Log in and register to view live content