Improving Variational Autoencoder Estimation from Incomplete Data with Mixture Variational Families
CoRR(2024)
摘要
We consider the task of estimating variational autoencoders (VAEs) when the
training data is incomplete. We show that missing data increases the complexity
of the model's posterior distribution over the latent variables compared to the
fully-observed case. The increased complexity may adversely affect the fit of
the model due to a mismatch between the variational and model posterior
distributions. We introduce two strategies based on (i) finite
variational-mixture and (ii) imputation-based variational-mixture distributions
to address the increased posterior complexity. Through a comprehensive
evaluation of the proposed approaches, we show that variational mixtures are
effective at improving the accuracy of VAE estimation from incomplete data.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要