Several scalable sample-based methods to compute the Kullback Leibler (KL) divergence between two distributions have been proposed and applied in large-scale machine learning models. While they have been found to be unstable, the theoretical root cause of the problem is not clear. In this paper, we study a generative adversarial network based approach that uses a neural network discriminator to estimate KL divergence. We argue that, in such case, high fluctuations in the estimates are a consequence of not controlling the complexity of the discriminator function space. We provide a theoretical underpinning and remedy for this problem by first constructing a discriminator in the Reproducing Kernel Hilbert Space (RKHS). This enables us to leverage sample complexity and mean embedding to theoretically relate the error probability bound of the KL estimates to the complexity of the discriminator in RKHS. Based on this theory, we then present a scalable way to control the complexity of the discriminator for a reliable estimation of KL divergence. We support both our proposed theory and method to control the complexity of the RKHS discriminator through controlled experiments.
翻译:在大规模机器学习模型中提出并应用了几种可缩放的样本基方法来计算两种分布之间的 Kullback Leiberr (KL) 差异。 虽然发现这些方法不稳定, 但其理论根源并不明确。 在本文中, 我们研究一种基于基因的对抗性网络方法, 使用神经网络歧视者来估计 KL 差异。 我们争辩说, 在这种情况下, 估计数的高度波动是无法控制歧视者功能空间复杂性的结果。 我们首先在生产 Kernel Hilbert 空间( RKHS) 中构建一个歧视者, 从而提供了这一问题的理论基础和补救方法。 这使我们能够利用 KL 估计数的样本复杂性, 并意味着嵌入到理论上将KL 估计数的误差概率与 RKHS 中歧视者的复杂性联系起来。 根据这一理论, 我们然后提出一种可扩展的方法来控制歧视者复杂性, 以便可靠地估计 KL 差异。 我们支持我们提出的理论和方法, 以控制RKHS 歧视者的复杂性。