Demixing structured superposition signals from periodic and aperiodic nonlinear observations

We consider the demixing problem of two (or more) structured high-dimensional vectors from a limited number of nonlinear observations where this nonlinearity is due to either a periodic or an aperiodic function. We study certain families of structured superposition models, and propose a method which provably recovers the components given (nearly) m = O (s) samples where s denotes the sparsity level of the underlying components. This strictly improves upon previous nonlinear demixing techniques and asymptotically matches the best possible sample complexity. We also provide a range of simulations to illustrate the performance of the proposed algorithms.

[1]  Piotr Indyk,et al.  Approximation Algorithms for Model-Based Compressive Sensing , 2014, IEEE Transactions on Information Theory.

[2]  E.J. Candes.  Compressive Sampling , 2022 .

[3]  Chinmay Hegde,et al.  Demixing sparse signals from nonlinear observations , 2016, 2016 50th Asilomar Conference on Signals, Systems and Computers.

[4]  Chinmay Hegde,et al.  Fast Algorithms for Demixing Sparse Signals From Nonlinear Observations , 2016, IEEE Transactions on Signal Processing.

[5]  Rebecca Willett,et al.  Matrix Completion Under Monotonic Single Index Models , 2015, NIPS.

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

[7]  Yaniv Plan,et al.  One‐Bit Compressed Sensing by Linear Programming , 2011, ArXiv.

[8]  Volkan Cevher,et al.  Convexity in Source Separation : Models, geometry, and algorithms , 2013, IEEE Signal Processing Magazine.

[9]  Joel A. Tropp,et al.  Sharp Recovery Bounds for Convex Demixing, with Applications , 2012, Found. Comput. Math..

[10]  C. Hegde,et al.  Iterative Thresholding for Demixing Structured Superpositions in High Dimensions , 2017, 1701.06597.

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

[12]  Y. Plan,et al.  High-dimensional estimation with geometric constraints , 2014, 1404.3749.

[13]  Adam Tauman Kalai,et al.  Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression , 2011, NIPS.

[14]  Stephen J. Wright,et al.  Forward — Backward greedy algorithms for signal demixing , 2014, 2014 48th Asilomar Conference on Signals, Systems and Computers.

[15]  Chinmay Hegde,et al.  A fast iterative algorithm for demixing sparse signals from nonlinear observations , 2016, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[16]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[17]  Yonina C. Eldar,et al.  Sparse Nonlinear Regression: Parameter Estimation and Asymptotic Inference , 2015, ArXiv.

[18]  Rachel Ward,et al.  New and Improved Johnson-Lindenstrauss Embeddings via the Restricted Isometry Property , 2010, SIAM J. Math. Anal..

[19]  Junzhou Huang,et al.  The Benefit of Group Sparsity , 2009 .

[20]  Chinmay Hegde,et al.  SPIN: Iterative signal recovery on incoherent manifolds , 2012, 2012 IEEE International Symposium on Information Theory Proceedings.

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

[22]  Deanna Needell,et al.  CoSaMP: Iterative signal recovery from incomplete and inaccurate samples , 2008, ArXiv.

[23]  Richard G. Baraniuk,et al.  1-Bit compressive sensing , 2008, 2008 42nd Annual Conference on Information Sciences and Systems.

[24]  Justin K. Romberg,et al.  Matched Filtering From Limited Frequency Samples , 2011, IEEE Transactions on Information Theory.

[25]  Ewout van den Berg,et al.  1-Bit Matrix Completion , 2012, ArXiv.

[26]  Michael Elad,et al.  Stable recovery of sparse overcomplete representations in the presence of noise , 2006, IEEE Transactions on Information Theory.

[27]  D. Donoho,et al.  Simultaneous cartoon and texture image inpainting using morphological component analysis (MCA) , 2005 .