Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted Data

Francesco Tonolini, Pablo Garcia Moreno, Andreas Damianou, Roderick Murray-Smith

Keywords: Missing value imputation, variational inference, variational auto-encoders

Abstract: We propose a new probabilistic method for unsupervised recovery of corrupted data. Given a large ensemble of degraded samples, our method recovers accurate posteriors of clean values, allowing the exploration of the manifold of possible reconstructed data and hence characterising the underlying uncertainty. In this set-ting, direct application of classical variational methods often gives rise to collapsed densities that do not adequately explore the solution space. Instead, we derive our novel reduced entropy condition approximate inference method that results in rich posteriors. We test our model in a data recovery task under the common setting of missing values and noise, demonstrating superior performance to existing variational methods for imputation and de-noising with different real data sets. We further show higher classification accuracy after imputation, proving the advantage of propagating uncertainty to downstream tasks with our model.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: Recovering accurate posterior distributions for unsupervised data recovery

Data: [Fashion-MNIST](https://paperswithcode.com/dataset/fashion-mnist)