Abstract
The iterative hard thresholding (IHT) algorithm is a powerful and efficient algorithm for solving \(\ell _0\)-regularized problems and inspired many applications in sparse-approximation and image-processing fields. Recently, some convergence results are established for the proximal scheme of IHT, namely proximal iterative hard thresholding (PIHT) algorithm (Blumensath and Davies, in J Fourier Anal Appl 14:629–654, 2008; Hu et al., Methods 67:294–303, 2015; Lu, Math Program 147:125–154, 2014; Trzasko et al., IEEE/SP 14th Workshop on Statistical Signal Processing, 2007) on solving the related \(\ell _0\)-optimization problems. However, the complexity analysis for the PIHT algorithm is not well explored. In this paper, we aim to provide some complexity estimations for the PIHT sequences. In particular, we show that the complexity of the sequential iterate error is at o(1 / k). Under the assumption that the objective function is composed of a quadratic convex function and \(\ell _0\) regularization, we show that the PIHT algorithm has \({\mathbb {R}}\)-linear convergence rate. Finally, we illustrate some applications of this algorithm for compressive sensing reconstruction and sparse learning and validate the estimated error bounds.
Similar content being viewed by others
References
Blumensath, T., Davies, M.E.: Iterative thresholding for sparse approximations. J. Fourier Anal. Appl. 14(5–6), 629–654 (2008)
Hu, Y.H., Li, C., Yang, X.Q.: Proximal gradient algorithm for group sparse optimization. Methods 67(3), 294–303 (2015)
Lu, Z.: Iterative hard thresholding methods for \(\ell _0\) regularized convex cone programming. Math. Program. 147(1–2), 125–154 (2014)
Trzasko, J., Manduca, A., Borisch, E.: Sparse mri reconstruction via multiscale l0-continuation. In: IEEE/SP 14th Workshop on Statistical Signal Processing, pp. 176–180 (2007)
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2(1), 183–202 (2009)
Chan, R., Chan, T., Shen, L., Shen, Z.: Wavelet algorithms for high-resolution image reconstruction. SIAM J. Sci. Comput. 24, 1408–1432 (2003)
Chan, R.H., Riemenschneider, S.D., Shen, L., Shen, Z.: Tight frame: an efficient way for high-resolution image reconstruction. Appl. Comput. Harmon. Anal. 17(1), 91–115 (2004)
Daubechies, I., Defrise, M., De Mol, C.: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 57(11), 1413–1457 (2004)
Nesterov, Y.: Smooth minimization of non-smooth functions. Math. Program. 103(1), 127–152 (2005)
Shen, Z., Toh, K.-C., Yun, S.: An accelerated proximal gradient algorithm for frame-based image restoration via the balanced approach. SIAM J. Imaging Sci. 4(2), 573–596 (2011)
Tseng, P.: On accelerated proximal gradient methods for convex–concave optimization. SIAM J. Optim. 12, 724–739 (2008)
Candès, E.J., Romberg, J., Tao, T.: Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inf. Theory 52(2), 489–509 (2006)
Zhang, X., Lu, Y., Chan, T.: A novel sparsity reconstruction method from poisson data for 3D bioluminescence tomography. J. Sci. Comput. 1, 17–32 (2012)
Dong, B., Zhang, Y.: An efficient algorithm for \(l_0\) minimization in wavelet frame based image restoration. J. Sci. Comput. 54(2–3), 350–368 (2013)
Zhang, Y., Dong, B., Zhaosong, L.: \(\ell _0\) minimization for wavelet frame based image restoration. Math. Comput. 82(282), 995–1015 (2013)
Fan, J., Li, R.: Variable selection via nonconcave penalized likelihood and its oracle properties. J. Am. Stat. Assoc. 96(456), 1348–1360 (2001)
Combettes, P.L., Wajs, V.R.: Signal recovery by proximal forward–backward splitting. Multiscale Model. Simul. 4(4), 1168–1200 (2005)
Lions, P.-L., Mercier, B.: Splitting algorithms for the sum of two nonlinear operators. SIAM J. Numer. Anal. 16(6), 964–979 (1979)
Blumensath, T., Davies, M.E.: Iterative hard thresholding for compressed sensing. Appl. Comput. Harmon. Anal. 27(3), 265–274 (2009)
Donoho, D.L.: Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289–1306 (2006)
Attouch, H., Bolte, J., Svaiter, B.F.: Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized gauss-seidel methods. Math. Program. 137(1–2), 91–129 (2013)
Bolte, J., Sabach, S., Teboulle, M.: Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. 146, 1–36 (2013)
Attouch, H., Bolte, J., Redont, P., Soubeyran, A.: Proximal alternating minimization and projection methods for nonconvex problems: an approach based on the kurdyka-łojasiewicz inequality. Math. Oper. Res. 35(2), 438–457 (2010)
Bao, C., Dong, B., Hou, L., Shen, Z., Zhang, X., Zhang, X.: Proximal iterative hard thresholding methods for wavelet frame based image restoration. CAM report 14-85, UCLA (2014)
Dong, Y.: The proximal point algorithm revisited. J. Optim. Theory Appl. 161(2), 478–489 (2014)
Hastie, T., Tibshirani, R., Friedman, J., Franklin, J.: The elements of statistical learning: data mining, inference and prediction. Math. Intel. 27(2), 83–85 (2005)
Lichman, M.: UCI machine learning repository (2013)
Acknowledgments
The authors would like to thank the anonymous reviewers for their helpful comments in improving the presentation of this paper.
Author information
Authors and Affiliations
Corresponding author
Additional information
The authors were partially supported by the National Natural Science Foundation of China (No. 91330102) and 973 program (No. 2015CB856000).
Rights and permissions
About this article
Cite this article
Zhang, X., Zhang, XQ. A Note on the Complexity of Proximal Iterative Hard Thresholding Algorithm. J. Oper. Res. Soc. China 3, 459–473 (2015). https://doi.org/10.1007/s40305-015-0105-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40305-015-0105-z
Keywords
- \(\ell _0\) Regularization
- Iterative hard thresholding
- Proximal algorithm
- Convergence rate
- \({\mathbb {R}}\)-linear