Improving Variational Autoencoder Estimation from Incomplete Data with Mixture Variational Families
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.
Code (1)
Tasks
ImputationSimilar Papers 제목 키워드 기반
Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data
Statistical models are central to machine learning with broad applicability across a range of downstream tasks. The models are controlled by free parameters that are typically estimated from data by maximum-likelihood es…
BIG-bench Machine LearningNormalising Flowsparameter estimationVariational InferenceEfficient Mixture Learning in Black-Box Variational Inference
Mixture variational distributions in black box variational inference (BBVI) have demonstrated impressive results in challenging density estimation tasks. However, currently scaling the number of mixture components can le…
Density EstimationVariational InferenceRecursive Inference for Variational Autoencoders
Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amorti…
Variational InferenceMixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
In this paper, we propose a latent-variable generative model called mixture of dynamical variational autoencoders (MixDVAE) to model the dynamics of a system composed of multiple moving sources. A DVAE model is pre-train…
Audio Source SeparationMulti-Object TrackingObject TrackingTrajectory ModelingTruncated Gaussian-Mixture Variational AutoEncoder
Variation Autoencoder (VAE) has become a powerful tool in modeling the non-linear generative process of data from a low-dimensional latent space. Recently, several studies have proposed to use VAE for unsupervised cluste…
ClusteringFunctional ConnectivityOutlier Detection