Compressed Sensing using Generative Models

The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain. For almost all results in this literature, the structure is represented by sparsity in a well-chosen basis. We show how to achieve guarantees similar to standard compressed sensing but without employing sparsity at all. Instead, we suppose that vectors lie near the range of a generative model G : ℝk → ℝn. Our main theorem is that, if G is L-Lipschitz, then roughly O(k log L) random Gaussian measurements suffice for an l2/l2 recovery guarantee. We demonstrate our results using generative models from published variational autoencoder and generative adversarial networks. Our method can use 5-10x fewer measurements than Lasso for the same accuracy.

[1]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[2]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[3]  Jiri Matousek,et al.  Lectures on discrete geometry , 2002, Graduate texts in mathematics.

[4]  E. Candès,et al.  Stable signal recovery from incomplete and inaccurate measurements , 2005, math/0503066.

[5]  D. Donoho,et al.  Sparse MRI: The application of compressed sensing for rapid MR imaging , 2007, Magnetic resonance in medicine.

[6]  R. DeVore,et al.  Compressed sensing and best k-term approximation , 2008 .

[7]  Jie Tang,et al.  Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic CT images from highly undersampled projection data sets. , 2008, Medical physics.

[8]  Lawrence Carin,et al.  Bayesian Compressive Sensing , 2008, IEEE Transactions on Signal Processing.

[9]  Ting Sun,et al.  Single-pixel imaging via compressive sampling , 2008, IEEE Signal Process. Mag..

[10]  Richard G. Baraniuk,et al.  Random Projections of Smooth Manifolds , 2009, Found. Comput. Math..

[11]  Bernard Chazelle,et al.  The Fast Johnson--Lindenstrauss Transform and Approximate Nearest Neighbors , 2009, SIAM J. Comput..

[12]  Martin J. Wainwright,et al.  A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers , 2009, NIPS.

[13]  Marco F. Duarte,et al.  Compressive sensing recovery of spike trains using a structured sparsity model , 2009 .

[14]  P. Bickel,et al.  SIMULTANEOUS ANALYSIS OF LASSO AND DANTZIG SELECTOR , 2008, 0801.1095.

[15]  Volkan Cevher,et al.  Model-Based Compressive Sensing , 2008, IEEE Transactions on Information Theory.

[16]  Martin J. Wainwright,et al.  Fast global convergence rates of gradient methods for high-dimensional statistical recovery , 2010, NIPS.

[17]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[18]  Martin J. Wainwright,et al.  Fast global convergence of gradient methods for high-dimensional statistical recovery , 2011, ArXiv.

[19]  Po-Ling Loh,et al.  High-dimensional regression with noisy and missing data: Provable guarantees with non-convexity , 2011, NIPS.

[20]  Julien Mairal,et al.  Optimization with Sparsity-Inducing Penalties , 2011, Found. Trends Mach. Learn..

[21]  Roman Vershynin,et al.  Introduction to the non-asymptotic analysis of random matrices , 2010, Compressed Sensing.

[22]  Chinmay Hegde,et al.  Signal Recovery on Incoherent Manifolds , 2012, IEEE Transactions on Information Theory.

[23]  D. L. Donoho,et al.  Compressed sensing , 2006, IEEE Trans. Inf. Theory.

[24]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[25]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[26]  Deanna Needell,et al.  Compressed Sensing and Dictionary Learning , 2014 .

[27]  Guillermo Sapiro,et al.  Video Compressive Sensing Using Gaussian Mixture Models , 2014, IEEE Transactions on Image Processing.

[28]  Rina Foygel,et al.  Corrupted Sensing: Novel Guarantees for Separating Structured Signals , 2013, IEEE Transactions on Information Theory.

[29]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[30]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[31]  S. Frick,et al.  Compressed Sensing , 2014, Computer Vision, A Reference Guide.

[32]  Piotr Indyk,et al.  A Nearly-Linear Time Framework for Graph-Structured Sparsity , 2015, ICML.

[33]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[35]  Minh N. Do,et al.  Semantic Image Inpainting with Perceptual and Contextual Losses , 2016, ArXiv.

[36]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[38]  Kibok Lee,et al.  Towards Understanding the Invertibility of Convolutional Neural Networks , 2017, IJCAI.

[39]  Subarna Tripathi,et al.  Precise Recovery of Latent Vectors from Generative Adversarial Networks , 2017, ICLR.

[40]  Minh N. Do,et al.  Semantic Image Inpainting with Deep Generative Models , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[42]  Anil A. Bharath,et al.  Inverting the Generator of a Generative Adversarial Network , 2016, IEEE Transactions on Neural Networks and Learning Systems.