[论文解读] Distribution Matching in Variational Inference

Mihaela Rosca, Balaji Lakshminarayanan+1 more|arXiv (Cornell University)|Feb 19, 2018

Generative Adversarial Networks and Image Synthesis参考文献 47被引用 50

一句话总结

本论文显示 VAE 无法在潜在空间与可见空间匹配边缘分布，使用密度比分析 VAE-GAN 混合模型，并得出当前的混合模型在可扩展性方面受限，且在样本质量上未超过 GAN。

ABSTRACT

With the increasingly widespread deployment of generative models, there is a mounting need for a deeper understanding of their behaviors and limitations. In this paper, we expose the limitations of Variational Autoencoders (VAEs), which consistently fail to learn marginal distributions in both latent and visible spaces. We show this to be a consequence of learning by matching conditional distributions, and the limitations of explicit model and posterior distributions. It is popular to consider Generative Adversarial Networks (GANs) as a means of overcoming these limitations, leading to hybrids of VAEs and GANs. We perform a large-scale evaluation of several VAE-GAN hybrids and analyze the implications of class probability estimation for learning distributions. While promising, we conclude that at present, VAE-GAN hybrids have limited applicability: they are harder to scale, evaluate, and use for inference compared to VAEs; and they do not improve over the generation quality of GANs.

研究动机与目标

• 表明 VAEs 难以在跨数据集和潜在变量维度的情况下，在潜在空间与可见空间匹配边缘分布。
• 分析显式分布与隐式分布在 VAEs 中如何影响分布匹配与学习。
• 使用密度比技巧评估 VAE-GAN 混合模型及其对似然估计与可扩展性的影响。
• 研究潜在空间边缘分布匹配在学习表示中的作用。
• 评估 VAE-GAN 混合模型在生成和推断方面是否比 VAE 与 GANs 具有实际优势。

提出的方法

• 推导并检验 ELBO 及其与边缘分布匹配与条件分布匹配的关系。
• 在 ColorMNIST、CelebA 与 CIFAR-10 上进行实验，以在不同后验和可见变量下量化边缘 KL: q(z)||p(z)。
• 应用密度比技巧，通过对抗自编码器和 AAE 使潜在空间实现隐式后验与边缘分布匹配。
• 引入并比较 VGH 与 VGH++ 变体，以在潜在空间和可见空间实现边缘分布匹配。
• 改用 Inception Score、多样性和 Wasserstein 判别器指标评估模型，而非 ELBO。
• 分析密度比估计如何影响似然界限与模型评估。

实验结果

研究问题

• RQ1 Can VAEs consistently match the marginal distributions in latent and visible spaces across datasets and latent dimensionalities?
• RQ2 Do explicit posteriors or explicit models limit marginal distribution matching more than conditional matching?
• RQ3 Do VAE-GAN hybrids improve sample quality or scalability compared to VAEs and GANs?
• RQ4 Does marginal distribution matching in latent space affect learned representations and inference capabilities?
• RQ5 Can density ratio tricks provide reliable likelihood bounds for evaluation in VAE-GAN hybrids?

主要发现

• VAEs fail to match the marginal latent posterior q(z) to the prior p(z) across datasets and latent sizes.
• Powerful explicit posteriors (e.g., RNVP) do not improve marginal distribution matching in VAEs.
• Using density ratio tricks in VAE-GAN hybrids leads to underestimation of the KL bound, harming model evaluation.
• Marginal distribution matching in latent space yields different latent representations, with AAEs learning denser representations than VAEs.
• Marginal distribution matching in visible space can improve generation quality but does not outperform pure GANs on sample quality metrics.
• VAE-GAN hybrids face scalability and hyperparameter sensitivity challenges and do not clearly outperform GANs in sample quality.