The Annals of Statistics

Optimal rates of convergence for noisy sparse phase retrieval via thresholded Wirtinger flow

T. Tony Cai, Xiaodong Li, and Zongming Ma

Full-text: Access denied (no subscription detected)

We're sorry, but we are unable to provide you with the full text of this article because we are not able to identify you as a subscriber. If you have a personal subscription to this journal, then please login. If you are already logged in, then you may need to update your profile to register your subscription. Read more about accessing full-text


This paper considers the noisy sparse phase retrieval problem: recovering a sparse signal $\mathbf{x}\in\mathbb{R}^{p}$ from noisy quadratic measurements $y_{j}=(\mathbf{a}_{j}'\mathbf{x})^{2}+\varepsilon_{j}$, $j=1,\ldots,m$, with independent sub-exponential noise $\varepsilon_{j}$. The goals are to understand the effect of the sparsity of $\mathbf{x}$ on the estimation precision and to construct a computationally feasible estimator to achieve the optimal rates adaptively. Inspired by the Wirtinger Flow [IEEE Trans. Inform. Theory 61 (2015) 1985–2007] proposed for non-sparse and noiseless phase retrieval, a novel thresholded gradient descent algorithm is proposed and it is shown to adaptively achieve the minimax optimal rates of convergence over a wide range of sparsity levels when the $\mathbf{a}_{j}$’s are independent standard Gaussian random vectors, provided that the sample size is sufficiently large compared to the sparsity of $\mathbf{x}$.

Article information

Ann. Statist., Volume 44, Number 5 (2016), 2221-2251.

Received: June 2015
Revised: January 2016
First available in Project Euclid: 12 September 2016

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62C20: Minimax procedures
Secondary: 62P35: Applications to physics

Iterative adaptive thresholding minimax rate non-convex empirical risk phase retrieval sparse recovery thresholded gradient method


Cai, T. Tony; Li, Xiaodong; Ma, Zongming. Optimal rates of convergence for noisy sparse phase retrieval via thresholded Wirtinger flow. Ann. Statist. 44 (2016), no. 5, 2221--2251. doi:10.1214/16-AOS1443.

Export citation


  • [1] Agarwal, A., Negahban, S. and Wainwright, M. J. (2012). Fast global convergence of gradient methods for high-dimensional statistical recovery. Ann. Statist. 40 2452–2482.
  • [2] Alexeev, B., Bandeira, A. S., Fickus, M. and Mixon, D. G. (2014). Phase retrieval with polarization. SIAM J. Imaging Sci. 7 35–66.
  • [3] Alon, N., Krivelevich, M. and Sudakov, B. (1998). Finding a large hidden clique in a random graph. In Proceedings of the Eighth International Conference “Random Structures and Algorithms” (Poznan, 1997) 13 457–466.
  • [4] Bauschke, H. H., Combettes, P. L. and Luke, D. R. (2002). Phase retrieval, error reduction algorithm, and Fienup variants: A view from convex optimization. J. Opt. Soc. Amer. A 19 1334–1345.
  • [5] Bentkus, V. (2003). An inequality for tail probabilities of martingales with differences bounded from one side. J. Theoret. Probab. 16 161–173.
  • [6] Berthet, Q. and Rigollet, P. (2013). Complexity theoretic lower bounds for sparse principal component detection. J. Mach. Learn. Res. (COLT) 30 1046–1066.
  • [7] Blumensath, T. and Davies, M. E. (2009). Iterative hard thresholding for compressed sensing. Appl. Comput. Harmon. Anal. 27 265–274.
  • [8] Cai, J., Candès, E. J. and Shen, Z. (2010). A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20 1956–1982.
  • [9] Candès, E. J., Eldar, Y. C., Strohmer, T. and Voroninski, V. (2013). Phase retrieval via matrix completion. SIAM J. Imaging Sci. 6 199–225.
  • [10] Candès, E. J. and Li, X. (2014). Solving quadratic equations via PhaseLift when there are about as many equations as unknowns. Found. Comput. Math. 14 1017–1026.
  • [11] Candès, E. J., Li, X. and Soltanolkotabi, M. (2015). Phase retrieval via Wirtinger flow: Theory and algorithms. IEEE Trans. Inform. Theory 61 1985–2007.
  • [12] Candès, E. J., Li, X. and Soltanolkotabi, M. (2015). Phase retrieval from coded diffraction patterns. Appl. Comput. Harmon. Anal. 39 277–299.
  • [13] Candès, E. J., Strohmer, T. and Voroninski, V. (2013). PhaseLift: Exact and stable signal recovery from magnitude measurements via convex programming. Comm. Pure Appl. Math. 66 1241–1274.
  • [14] Chai, A., Moscoso, M. and Papanicolaou, G. (2011). Array imaging using intensity-only measurements. Inverse Probl. 27 015005, 16.
  • [15] Chen, Y. and Candès, E. C. (2015). Solving Random Quadratic Systems of Equations is Nearly as Easy as Solving Linear Systems. Advances in Neural Information Processing Systems 34 739–747. Curran Associates, Red Hook, NY.
  • [16] Chen, Y., Chi, Y. and Goldsmith, A. J. (2015). Exact and stable covariance estimation from quadratic sampling via convex programming. IEEE Trans. Inform. Theory 61 4034–4059.
  • [17] Daubechies, I., Defrise, M. and De Mol, C. (2004). An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Comm. Pure Appl. Math. 57 1413–1457.
  • [18] El Karoui, N., Bean, D., Bickel, P. J., Lim, C. and Yu, B. (2013). On robust regression with high-dimensional predictors. PNAS 110 14557–14562.
  • [19] Fienup, J. R. (1982). Phase retrieval algorithms: A comparison. Appl. Opt. 21 2758–2769.
  • [20] Gao, C., Ma, Z. and Zhou, H. H. (2014) Sparse CCA: Adaptive estimation and computational barriers. Preprint. Available at arXiv:1409.8565.
  • [21] Gerchberg, R. W. and Saxton, W. O. (1972). A practical algorithm for the determination of phase from image and diffraction plane pictures. Optik 35 237–246.
  • [22] Jaganathan, K., Oymak, S. and Hassibi, B. (2012). On robust phase retrieval for sparse signals. In 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello 794–799. IEEE, Piscataway, NJ.
  • [23] Jain, P., Tewariy, A. and Kar, P. (2014). On iterative hard thresholding methods for high-dimensional $M$-estimation. In Advances in Neural Information Processing Systems 27 685–693. Curran Associates, Red Hook, NY.
  • [24] Johnstone, I. M. (2013). Gaussian estimation: Sequence and wavelet models. Available at
  • [25] Johnstone, I. M. and Lu, A. Y. (2009). On consistency and sparsity for principal components analysis in high dimensions. J. Amer. Statist. Assoc. 104 682–693.
  • [26] Keshavan, R. H., Montanari, A. and Oh, S. (2010). Matrix completion from a few entries. IEEE Trans. Inform. Theory 56 2980–2998.
  • [27] Laurent, B. and Massart, P. (2000). Adaptive estimation of a quadratic functional by model selection. Ann. Statist. 28 1302–1338.
  • [28] Lecué, G. and Mendelson, S. (2013). Minimax rates of convergence and the performance of ERM in phase recovery. Electron. J. Probab. 20 1–29.
  • [29] Lee, K., Wu, Y. and Bresler, Y. (2013). Near optimal compressed sensing of sparse rank-one matrices via sparse power factorization. Preprint. Available at arXiv:1312.0525.
  • [30] Levi, A. and Stark, H. (1984). Image restoration by the method of generalized projections with application to restoration from magnitude. J. Opt. Soc. Amer. A 1 932–943.
  • [31] Li, X. and Voroninski, V. (2013). Sparse signal recovery from quadratic measurements via convex programming. SIAM J. Math. Anal. 45 3019–3033.
  • [32] Loh, P. and Wainwright, M. J. (2015), Regularized $m$-estimators with nonconvexity: Statistical and algorithmic theory for local optima. J. Mach. Learn. Res. 16 559–616.
  • [33] Ma, Z. (2013). Sparse principal component analysis and iterative thresholding. Ann. Statist. 41 772–801.
  • [34] Maleki, A. and Donoho, D. L. (2010). Optimally tuned iterative reconstruction algorithms for compressed sensing. IEEE J. Sel. Top. Signal Process. 4 330–341.
  • [35] Marchesini, S., Tu, Y. C. and Wu, H. (2014). Alternating projection, ptychographic imaging and phase synchronization. Appl. Comput. Harmon. Anal. To appear. Available at arXiv:1402.0550.
  • [36] Needell, D. and Tropp, J. A. (2009). CoSaMP: Iterative signal recovery from incomplete and inaccurate samples. Appl. Comput. Harmon. Anal. 26 301–321.
  • [37] Netrapalli, P., Jain, P. and Sanghavi, S. (2015). Phase retrieval using alternating minimization. IEEE Trans. Signal Process. 63 4814–4826.
  • [38] Oymak, S., Jalali, A., Fazel, M., Eldar, Y. C. and Hassibi, B. (2015). Simultaneously structured models with application to sparse and low-rank matrices. IEEE Trans. Inform. Theory 61 2886–2908.
  • [39] Schniter, P. and Rangan, S. (2012). Compressive phase retrieval via generalized approximate message passing. In 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello 815–822. IEEE, Piscataway, NJ.
  • [40] Shechtman, Y., Beck, A. and Eldar, Y. C. (2014). GESPAR: Efficient phase retrieval of sparse signals. IEEE Trans. Signal Process. 62 928–938.
  • [41] Shechtman, Y., Eldar, Y. C., Cohen, O., Chapman, H. N., Miao, J. and Segev, M. (2014). Phase retrieval with application to optical imaging: A contemporary overview. IEEE Signal Process. Mag. 32. To appear. Available at arXiv:1402.7350.
  • [42] Soltanolkotabi, M. (2014). Algorithms and theory for clustering and nonconvex quadratic programming. PhD dissertatin, Stanford Univ., Stanford, CA.
  • [43] Vershynin, R. (2012). Introduction to the non-asymptotic analysis of random matrices. In Compressed Sensing 210–268. Cambridge Univ. Press, Cambridge.
  • [44] Waldspurger, I., d’Aspremont, A. and Mallat, S. (2015). Phase recovery, maxcut and complex semidefinite programming. Math. Program. 149 47–81.
  • [45] Wang, T., Berthet, Q. and Samworth, R. J. (2014). Statistical and computational trade-offs in estimation of sparse principal components. Ann. Statist.. To appear. Available at arXiv:1408.5369.
  • [46] Wang, Z., Liu, H. and Zhang, T. (2014). Optimal computational and statistical rates of convergence for sparse nonconvex learning problems. Ann. Statist. 42 2164–2201.
  • [47] Yuan, X., Li, P. and Zhang, T. (2014). Gradient hard thresholding pursuit for sparsity-constrained optimization. In International Conference on Machine Learning (ICML 2014), Beijing, China.
  • [48] Yuan, X. and Zhang, T. (2013). Truncated power method for sparse eigenvalue problems. J. Mach. Learn. Res. 14 899–925.