On the Implicit Assumptions of GANs
arXiv:1811.12402
Abstract
Generative adversarial nets (GANs) have generated a lot of excitement. Despite their popularity, they exhibit a number of well-documented issues in practice, which apparently contradict theoretical guarantees. A number of enlightening papers have pointed out that these issues arise from unjustified assumptions that are commonly made, but the message seems to have been lost amid the optimism of recent years. We believe the identified problems deserve more attention, and highlight the implications on both the properties of GANs and the trajectory of research on probabilistic models. We recently proposed an alternative method that sidesteps these problems.
arXiv comment8 pages
References in corpus (8)
- f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
- Towards Principled Methods for Training Generative Adversarial Networks
- How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
- Learning in Implicit Generative Models
- On distinguishability criteria for estimating generative models
- Implicit Maximum Likelihood Estimation
- Likelihood-free inference via classification
- Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training
Cited by in corpus (6)
- Generative deep learning as a tool for inverse design of high-entropy refractory alloys
- Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds
- Deconstructing Generative Adversarial Networks
- Towards A Multi-agent System for Online Hate Speech Detection
- A Novel Framework for Selection of GANs for an Application
- Exploiting the Hidden Tasks of GANs: Making Implicit Subproblems Explicit