Markov chain Monte Carlo (MCMC), such as Langevin dynamics, is valid for approximating intractable distributions. However, its usage is limited in the context of deep latent variable models owing to costly datapoint-wise sampling iterations and slow convergence. This paper proposes the amortized Langevin dynamics (ALD), wherein datapoint-wise MCMC iterations are entirely replaced with updates of an encoder that maps observations into latent variables. This amortization enables efficient posterior sampling without datapoint-wise iterations. Despite its efficiency, we prove that ALD is valid as an MCMC algorithm, whose Markov chain has the target posterior as a stationary distribution under mild assumptions. Based on the ALD, we also present a new deep latent variable model named the Langevin autoencoder (LAE). Interestingly, the LAE can be implemented by slightly modifying the traditional autoencoder. Using multiple synthetic datasets, we first validate that ALD can properly obtain samples from target posteriors. We also evaluate the LAE on the image generation task, and show that our LAE can outperform existing methods based on variational inference, such as the variational autoencoder, and other MCMC-based methods in terms of the test likelihood.
翻译:诸如 Langevin 等 Markov 链子 Monte Carlo (MCMC ), 诸如 Langevin 动态等 的 Markov 链子(MCMC ) 有效, 可用于 近似棘手的分布。 然而, 由于数据点抽样迭代成本高且趋同缓慢, 它的使用在深潜变量模型中是有限的。 本文建议了分解 Langevin 动态(ALD ), 数据点的 MMC 迭代完全被更新的编码器所取代, 该编码器将观测结果映射为潜伏变量。 这种摊还使得在没有数据点迭代法的情况下高效的后部取样。 尽管它效率很高, 我们证明 ALD 是一种 MC 算法是有效的, 其 Markov 链子 将目标后部的后部序列作为在轻度假设条件下的固定分布。 根据 ALD, 我们还提出了一个新的深潜潜伏变量模型, 名为 Langevin 自动coder 。 。 有趣的是, 我们用多种合成数据集,, 我们首先确认 ALD 能从目标的海报 获取样本。