论文标题
合作或竞争：关于生成网络培训的新观点
Cooperate or Compete: A New Perspective on Training of Generative Networks
论文作者
论文摘要
GAN有两个竞争模块：对发电机模块进行了训练以生成新的示例，并且对歧视器模块进行了训练，以区分真实示例与生成的示例。 GAN的训练过程被建模为有限重复的同时游戏。每个模块都试图以非合件的方式在基本游戏的每次重复（每批培训数据）中提高其性能。我们观察到，如果将培训模仿为无限重复的同时游戏，则每个模块都可以表现更好，并且可以更快地学习。在每次重复基础游戏（每批训练数据）中，更强的模块（其性能会提高或与以前的培训数据相比保持相同）与较弱的模块（与先前的培训数据相比，其性能降低），并且只有较弱的模块才能提高其性能。
GANs have two competing modules: the generator module is trained to generate new examples, and the discriminator module is trained to discriminate real examples from generated examples. The training procedure of GAN is modeled as a finitely repeated simultaneous game. Each module tries to increase its performance at every repetition of the base game (at every batch of training data) in a non-cooperative manner. We observed that each module can perform better and learn faster if training is modeled as an infinitely repeated simultaneous game. At every repetition of the base game (at every batch of training data) the stronger module (whose performance is increased or remains the same compared to the previous batch of training data) cooperates with the weaker module (whose performance is decreased compared to the previous batch of training data) and only the weaker module is allowed to increase its performance.
