A study of traits that affect learnability in GANs
arXiv:2011.13728
Abstract
Generative Adversarial Networks GANs are algorithmic architectures that use two neural networks, pitting one against the opposite so as to come up with new, synthetic instances of data that can pass for real data. Training a GAN is a challenging problem which requires us to apply advanced techniques like hyperparameter tuning, architecture engineering etc. Many different losses, regularization and normalization schemes, network architectures have been proposed to solve this challenging problem for different types of datasets. It becomes necessary to understand the experimental observations and deduce a simple theory for it. In this paper, we perform empirical experiments using parameterized synthetic datasets to probe what traits affect learnability.
References in corpus (5)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- A note on the evaluation of generative models
- How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
- Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data