论文标题
使用对抗梯度估计的双向生成建模
Bidirectional Generative Modeling Using Adversarial Gradient Estimation
论文作者
论文摘要
本文认为，双向生成建模的一般$ f $ divergence配方，其中包括VAE和Bigan作为特殊情况。我们为此公式提供了一种新的优化方法，其中使用对抗学会的歧视器计算梯度。在我们的框架中，我们表明不同的差异在梯度评估方面诱导了相似的算法，除了不同的缩放。因此，本文提供了一类基于$ f $ divergence的生成建模方法的一类食谱。提供了理论上的理由和广泛的经验研究，以证明我们的方法比现有方法的优势。
This paper considers the general $f$-divergence formulation of bidirectional generative modeling, which includes VAE and BiGAN as special cases. We present a new optimization method for this formulation, where the gradient is computed using an adversarially learned discriminator. In our framework, we show that different divergences induce similar algorithms in terms of gradient evaluation, except with different scaling. Therefore this paper gives a general recipe for a class of principled $f$-divergence based generative modeling methods. Theoretical justifications and extensive empirical studies are provided to demonstrate the advantage of our approach over existing methods.
