Estimating conditional density of missing values using deep Gaussian mixture model
This work addresses missing data imputation, a common issue in data analysis, but appears incremental as it combines existing deep neural networks with Gaussian mixture models.
The paper tackles the problem of estimating the conditional probability distribution of missing values given observed data, proposing a deep Gaussian mixture model that achieves better log-likelihood than a typical conditional GMM and produces visually plausible imputations.
We consider the problem of estimating the conditional probability distribution of missing values given the observed ones. We propose an approach, which combines the flexibility of deep neural networks with the simplicity of Gaussian mixture models (GMMs). Given an incomplete data point, our neural network returns the parameters of Gaussian distribution (in the form of Factor Analyzers model) representing the corresponding conditional density. We experimentally verify that our model provides better log-likelihood than conditional GMM trained in a typical way. Moreover, imputation obtained by replacing missing values using the mean vector of our model looks visually plausible.