Abstract
This chapter develops a theoretical analysis of the convex programming method for recovering a structured signal from independent random linear measurements. This technique delivers bounds for the sampling complexity that are similar to recent results for standard Gaussian measurements, but the argument applies to a much wider class of measurement ensembles. To demonstrate the power of this approach, the chapter presents a short analysis of phase retrieval by trace-norm minimization. The key technical tool is a framework, due to Mendelson and coauthors, for bounding a nonnegative empirical process.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The extended real numbers \(\overline{\mathbb{R}}:= \mathbb{R} \cup \{\pm \infty \}\). A proper convex function takes at least one finite value but never the value \(-\infty \).
- 2.
A Rademacher random variable takes the two values ± 1 with equal probability.
References
D. Amelunxen, M. Lotz, M.B. McCoy, J.A. Tropp, Living on the edge: phase transitions in convex programs with random data. Inf. Inference 3(3), 224–294 (2014). Available at http://arXiv.org/abs/1303.6672
R. Balan, B.G. Bodmann, P.G. Casazza, D. Edidin, Painless reconstruction from magnitudes of frame coefficients. J. Fourier Anal. Appl. 15(4), 488–501 (2009)
S. Boucheron, G. Lugosi, P. Massart, Concentration Inequalities: A Nonasymptotic Theory of Independence (Oxford University Press, Oxford, 2013)
T.T. Cai, T. Liang, A. Rakhlin, Geometrizing local rates of convergence for linear inverse problems (April 2014). Available at http://arXiv.org/abs/1404.4408
E.J. Candès, T. Strohmer, V. Voroninski, PhaseLift: exact and stable signal recovery from magnitude measurements via convex programming. Commun. Pure Appl. Math. 66(8), 1241–1274 (2013)
V. Chandrasekaran, B. Recht, P.A. Parrilo, A.S. Willsky, The convex geometry of linear inverse problems. Found. Comput. Math. 12(6), 805–849 (2012)
R.Y. Chen, A. Gittens, J.A. Tropp, The masked sample covariance estimator: an analysis via the matrix Laplace transform method. Inf. Inference 1, 2–20 (2012)
K.R. Davidson, S.J. Szarek, Local operator theory, random matrices and Banach spaces, in Handbook of the Geometry of Banach Spaces, vol. I (North-Holland, Amsterdam, 2001), pp. 317–366
M. Fazel. Matrix Rank Minimization with Applications. Ph.D. thesis, Stanford University, 2002.
R. Foygel, L. Mackey, Corrupted sensing: novel guarantees for separating structured signals. Trans. Inf. Theory 60(2), 1223–1247 (2014)
Y. Gordon, Some inequalities for Gaussian processes and applications. Isr. J. Math. 50(4), 265–289 (1985)
Y. Gordon. On Milman’s inequality and random subspaces which escape through a mesh in \(\mathbf{R}^{n}\), in Geometric Aspects of Functional Analysis (1986/1987). Lecture Notes in Mathematics, vol. 1317 (Springer, Berlin, 1988), pp. 84–106
D. Gross, Recovering low-rank matrices from few coefficients in any basis. IEEE Trans. Inf. Theory 57(3), 1548–1566 (2011)
V. Koltchinskii, S. Mendelson, Bounding the smallest singular value of a random matrix without concentration (December 2013). Available at http://arXiv.org/abs/1312.3580
R. Latała, K. Oleszkiewicz, On the best constant in the Khinchin-Kahane inequality. Studia Math. 109(1), 101–104 (1994)
G. Lecué, S. Mendelson, Compressed sensing under weak moment assumptions (January 2014). Available at http://arXiv.org/abs/1401.2188
M. Ledoux, M. Talagrand, Probability in Banach Spaces: Isoperimetry and Processes (Springer, Berlin, 1991)
S. Mendelson. Empirical processes with a bounded \(\psi _{1}\) diameter. Geom. Funct. Anal. 20(4), 988–1027 (2010)
S. Mendelson, A remark on the diameter of random sections of convex bodies (December 2013). Available at http://arXiv.org/abs/1312.3608
S. Mendelson, Learning without concentration. J. Assoc. Comput. Mach. (2014, to appear). 62(3), (2015). Available at http://arXiv.org/abs/1401.0304
S. Mendelson, Learning without concentration for general loss functions (October 2014). Available at http://arXiv.org/abs/1410.3192
S. Mendelson, A. Pajor, N. Tomczak-Jaegermann, Reconstruction and subgaussian operators in asymptotic geometric analysis. Geom. Funct. Anal. 17(4), 1248–1282 (2007)
V. Milman, G. Schechtman, Asymptotic Theory of Finite-Dimensional Normed Linear Spaces. Number 1200 in LNM (Springer, New York, 1986)
S. Oymak, B. Hassibi, New null space results and recovery thresholds for matrix rank minimization. Partial results presented at ISIT 2011 (2010). Available at http://arXiv.org/abs/1011.6326
S. Oymak, B. Hassibi, Sharp MSE bounds for proximal denoising. Partial results presented at Allerton 2012 (March 2013). Available at http://arxiv.org/abs/1305.2714
S. Oymak, C. Thrampoulides, B. Hassibi, Simple bounds for noisy linear inverse problems with exact side information (December 2013). Available at http://arXiv.org/abs/1312.0641
G. Pisier, The Volume of Convex Bodies and Banach Space Geometry (Cambridge University Press, Cambridge, 1989)
R.T. Rockafellar, Convex Analysis (Princeton University Press, Princeton, 1970)
M. Rudelson, R. Vershynin, On sparse reconstruction from Fourier and Gaussian measurements. Commun. Pure Appl. Math. 61(8), 1025–1045 (2008)
M. Sion, On general minimax theorems. Pac. J. Math. 8, 171–176 (1958)
M. Stojnic, Various thresholds for â„“ 1-optimization in compressed sensing (2009). Available at http://arXiv.org/abs/0907.3666
M. Talagrand, The Generic Chaining. Upper and Lower Bounds of Stochastic Processes. Springer Monographs in Mathematics (Springer, Berlin, 2005)
C. Thrampoulides, S. Oymak, B. Hassibi, Simple error bounds for regularized noisy linear inverse problems. Appeared at ISIT 2014 (January 2014). Available at http://arXiv.org/abs/1401.6578
J. Tropp, M. Wakin, M. Duarte, D. Baron, R. Baraniuk, Random filters for compressive sampling and reconstruction, in Proceedings of the 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, 2006 (ICASSP 2006), vol. 3, May 2006, pp. III–875
A.W. van der Vaart, J.A. Wellner, Weak Convergence and Empirical Processes. Springer Series in Statistics (Springer, New York, 1996). With applications to statistics.
R. Vershynin, Introduction to the non-asymptotic analysis of random matrices, in Compressed Sensing (Cambridge University Press, Cambridge, 2012), pp. 210–268
G.A. Watson, Characterization of the subdifferential of some matrix norms. Linear Algebra Appl. 170, 33–45 (1992)
Acknowledgements
JAT gratefully acknowledges support from ONR award N00014-11-1002, AFOSR award FA9550-09-1-0643, and a Sloan Research Fellowship. Thanks are also due to the Moore Foundation.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Tropp, J.A. (2015). Convex Recovery of a Structured Signal from Independent Random Linear Measurements. In: Pfander, G. (eds) Sampling Theory, a Renaissance. Applied and Numerical Harmonic Analysis. Birkhäuser, Cham. https://doi.org/10.1007/978-3-319-19749-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-19749-4_2
Publisher Name: Birkhäuser, Cham
Print ISBN: 978-3-319-19748-7
Online ISBN: 978-3-319-19749-4
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)