Smoothness and Stability in GANs
This addresses training instability in GANs for machine learning practitioners, but it is incremental as it builds on existing theoretical insights.
The paper tackled the problem of unstable training in GANs by developing a theoretical framework to understand stability, deriving conditions for generator stationarity, and constructing a GAN that satisfies these conditions, explaining existing stabilization techniques.
Generative adversarial networks, or GANs, commonly display unstable behavior during training. In this work, we develop a principled theoretical framework for understanding the stability of various types of GANs. In particular, we derive conditions that guarantee eventual stationarity of the generator when it is trained with gradient descent, conditions that must be satisfied by the divergence that is minimized by the GAN and the generator's architecture. We find that existing GAN variants satisfy some, but not all, of these conditions. Using tools from convex analysis, optimal transport, and reproducing kernels, we construct a GAN that fulfills these conditions simultaneously. In the process, we explain and clarify the need for various existing GAN stabilization techniques, including Lipschitz constraints, gradient penalties, and smooth activation functions.