We are excited to announce that the paper "Posterior Consistency for Missing Data in Variational Autoencoders" by Timur Sudak and Sebastian Tschiatschek has been accepted at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML/PKDD 2023) with an acceptance rate of ~24%.
Have a look at our paper to learn how to regularize a variational autoencoder's posterior in the face of missing data to achieve better performance.
Paper accepted at ECML 2023
