NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:6481
Title:Adaptive Density Estimation for Generative Models

This paper proposes a new hybrid generative model, combining a maximum-likelihood approach with GANs. The authors are to be commended for their practical and conceptually interesting work. In the final version, the paper would also benefit from a discussion of [1], related work that introduces an alternative maximum likelihood perspective of GANs, and provides Bayesian generalizations. [1] Saatchi, Y and Wilson, A.G. Bayesian GAN. NeurIPS 2017.