Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization
[edit]
Proceedings of Machine Learning Research, PMLR 89:25142524, 2019.
Abstract
Compressed sensing techniques enable efficient acquisition and recovery of sparse, highdimensional data signals via lowdimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised representation learning inspired by compressed sensing. We treat the lowdimensional projections as noisy latent representations of an autoencoder and directly learn both the acquisition (i.e., encoding) and amortized recovery (i.e., decoding) procedures. Our learning objective optimizes for a tractable variational lower bound to the mutual information between the datapoints and the latent representations. We show how our framework provides a unified treatment to several lines of research in dimensionality reduction, compressed sensing, and generative modeling. Empirically, we demonstrate a 32% improvement on average over competing approaches for the task of statistical compressed sensing of highdimensional datasets.
Related Material


