Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization

Aditya Grover, Stefano Ermon
Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, PMLR 89:2514-2524, 2019.

Abstract

Compressed sensing techniques enable efficient acquisition and recovery of sparse, highdimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised representation learning inspired by compressed sensing. We treat the low-dimensional 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 high-dimensional datasets.

Cite this Paper


BibTeX
@InProceedings{pmlr-v89-grover19a, title = {Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization}, author = {Grover, Aditya and Ermon, Stefano}, booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics}, pages = {2514--2524}, year = {2019}, editor = {Chaudhuri, Kamalika and Sugiyama, Masashi}, volume = {89}, series = {Proceedings of Machine Learning Research}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v89/grover19a/grover19a.pdf}, url = {http://proceedings.mlr.press/v89/grover19a.html}, abstract = {Compressed sensing techniques enable efficient acquisition and recovery of sparse, highdimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised representation learning inspired by compressed sensing. We treat the low-dimensional 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 high-dimensional datasets.} }
Endnote
%0 Conference Paper %T Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization %A Aditya Grover %A Stefano Ermon %B Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-grover19a %I PMLR %P 2514--2524 %U http://proceedings.mlr.press/v89/grover19a.html %V 89 %X Compressed sensing techniques enable efficient acquisition and recovery of sparse, highdimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised representation learning inspired by compressed sensing. We treat the low-dimensional 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 high-dimensional datasets.
APA
Grover, A. & Ermon, S.. (2019). Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization. Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 89:2514-2524 Available from http://proceedings.mlr.press/v89/grover19a.html.

Related Material