论文标题
学习断开的流形：无剂土地
Learning disconnected manifolds: a no GANs land
论文作者
论文摘要
生成的对抗性网络的典型体系结构利用了连续发生器转换的单峰潜伏分布。因此，建模的分布始终具有连接的支持，在学习一组歧管集合时，这很麻烦。我们通过建立一个无免费的午餐定理来为断开的多种流形学习提供正式的问题，以说明对目标分布的精确度上的上限。这是通过建立必要的低质量区域的必要存在来完成的，在该区域中，发电机在两个断开模式之间连续采样数据。最后，我们根据发电机的规范得出了一种拒绝采样方法，并在包括Biggan在内的多个发电机上显示了其效率。
Typical architectures of Generative AdversarialNetworks make use of a unimodal latent distribution transformed by a continuous generator. Consequently, the modeled distribution always has connected support which is cumbersome when learning a disconnected set of manifolds. We formalize this problem by establishing a no free lunch theorem for the disconnected manifold learning stating an upper bound on the precision of the targeted distribution. This is done by building on the necessary existence of a low-quality region where the generator continuously samples data between two disconnected modes. Finally, we derive a rejection sampling method based on the norm of generators Jacobian and show its efficiency on several generators including BigGAN.
