arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1509.00519cs.LGstat.ML
收藏

重要性加权自动编码器

Importance Weighted Autoencoders

University of Toronto(多伦多大学)

Yuri Burda, Roger Grosse, Ruslan Salakhutdinov

摘要:

变分自编码器(VAE; Kingma,Welling(2014))是最近提出的生成模型,其将自顶向下的生成网络与近似后验推理的自底向上的识别网络配对。它通常对后验推断做出强假设,例如后验分布近似为阶乘,并且其参数可以通过观察值的非线性回归近似。正如我们经验所示,VAE目标可能导致过度简化的表示,无法使用网络的整个建模能力。我们提出的重要性加权自动编码器(IWAE),生成模型与相同的架构的VAE,但它使用严格的更严格的对数似然下界来自重要性加权。在IWAE中,识别网络使用多个样本来近似后验,从而增加了对不符合VAE建模假设的复杂后验建模的灵活性。我们的经验表明,IWAE学习更丰富的潜在空间表示比VAE,导致密度估计基准测试对数似然改进。

英文摘要:

The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong assumptions about posterior inference, for instance that the posterior distribution is approximately factorial, and that its parameters can be approximated with nonlinear regression from the observations. As we show empirically, the VAE objective can lead to overly simplified representations which fail to use the network's entire modeling capacity. We present the importance weighted autoencoder (IWAE), a generative model with the same architecture as the VAE, but which uses a strictly tighter log-likelihood lower bound derived from importance weighting. In the IWAE, the recognition network uses multiple samples to approximate the posterior, giving it increased flexibility to model complex posteriors which do not fit the VAE modeling assumptions. We show empirically that IWAEs learn richer latent space representations than VAEs, leading to improved test log-likelihood on density estimation benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑