Stochastic Deconvolutional Neural Network Ensemble Training on Generative Pseudo-Adversarial Networks
This addresses training stability issues for researchers and practitioners using GANs, though it appears incremental as it builds on existing ensemble methods.
The paper tackles the training instability problems in Generative Adversarial Networks (GANs), such as oscillation between generator and discriminator, imbalance in learning capacity, and mode collapse, by proposing stochastic ensembling as a method to improve stability during training.
The training of Generative Adversarial Networks is a difficult task mainly due to the nature of the networks. One such issue is when the generator and discriminator start oscillating, rather than converging to a fixed point. Another case can be when one agent becomes more adept than the other which results in the decrease of the other agent's ability to learn, reducing the learning capacity of the system as a whole. Additionally, there exists the problem of Mode Collapse which involves the generators output collapsing to a single sample or a small set of similar samples. To train GANs a careful selection of the architecture that is used along with a variety of other methods to improve training. Even when applying these methods there is low stability of training in relation to the parameters that are chosen. Stochastic ensembling is suggested as a method for improving the stability while training GANs.