Gradient Estimators for Implicit Models

Yingzhen Li, Richard E. Turner

Feb 15, 2018 (modified: Feb 23, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: Implicit models, which allow for the generation of samples but not for point-wise evaluation of probabilities, are omnipresent in real-world problems tackled by machine learning and a hot topic of current research. Some examples include data simulators that are widely used in engineering and scientific research, generative adversarial networks (GANs) for image synthesis, and hot-off-the-press approximate inference techniques relying on implicit distributions. The majority of existing approaches to learning implicit models rely on approximating the intractable distribution or optimisation objective for gradient-based optimisation, which is liable to produce inaccurate updates and thus poor models. This paper alleviates the need for such approximations by proposing the \emph{Stein gradient estimator}, which directly estimates the score function of the implicitly defined distribution. The efficacy of the proposed estimator is empirically demonstrated by examples that include meta-learning for approximate inference and entropy regularised GANs that provide improved sample diversity.
  • TL;DR: We introduced a novel gradient estimator using Stein's method, and compared with other methods on learning implicit models for approximate inference and image generation.
  • Keywords: Implicit Models, Approximate Inference, Deep Learning