论文标题
甘斯的平稳性和稳定性
Smoothness and Stability in GANs
论文作者
论文摘要
生成的对抗网络或gans通常在训练过程中表现出不稳定的行为。在这项工作中，我们开发了一个原则性的理论框架，以理解各种类型的gan的稳定性。特别是，我们得出条件，可以保证发电机经过梯度下降训练时最终的平稳性，必须通过gan和发电机的架构最小化的差异来满足的条件。我们发现现有的GAN变体满足了这些条件中的一些但并非全部。使用凸分析，最佳传输和再现内核中的工具，我们构建了一个同时满足这些条件的gan。在此过程中，我们解释并阐明了对各种现有的GAN稳定技术的需求，包括Lipschitz的约束，梯度惩罚和平滑的激活功能。
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.
