Abstract
Non-convex regularization has been recognized as an especially important approach in recent studies to promote sparsity. In this paper, we study the non-convex piecewise quadratic approximation (PQA) regularization for sparse solutions of the linear inverse problem. It is shown that exact recovery of sparse signals and stable recovery of compressible signals are possible through local optimum of this regularization. After developing a thresholding representation theory for PQA regularization, we propose an iterative PQA thresholding algorithm (PQA algorithm) to solve this problem. The PQA algorithm converges to a local minimizer of the regularization, with an eventually linear convergence rate. Furthermore, we adopt the idea of accelerated gradient method to design the accelerated iterative PQA thresholding algorithm (APQA algorithm), which is also linearly convergent, but with a faster convergence rate. Finally, we carry out a series of numerical experiments to assess the performance of both algorithms for PQA regularization. The results show that PQA regularization outperforms \(\ell _1\) and \(\ell _{1/2}\) regularizations in terms of accuracy and sparsity, while the APQA algorithm is demonstrated to be significantly better than the PQA algorithm.
Similar content being viewed by others
References
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2, 183–202 (2009)
Blumensath, T., Davies, M.E.: Iterative hard thresholding for compressed sensing. Appl. Comput. Harmon. Anal. 27(3), 265–274 (2008)
Blumensath, T., Davies, M.E.: Iterative thresholding for sparse approximations. J. Fourier Anal. Appl 14, 629–654 (2008)
Bruckstein, A.M., Donoho, D.L., Elad, M.: From sparse solutions of systems of equations to sparse modeling of signals and images. SIAM Rev. 51(1), 34–81 (2009)
Candes, E.J., Recht, B.: Exact matrix completion via convex optimization. Found. Comput. Math. 9(6), 717–772 (2008)
Candes, 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)
Candes, E.J., Wakin, M.B., Boyd, S.P.: Enhancing sparsity by reweighted \(l_{1}\) minimization. J. Fourier Anal. Appl. 14, 877–905 (2008)
Cao, W.F., Sun, J., Xu, Z.B.: Fast image deconvolution using closed-form thresholding formulas of lq (q=1/2,2/3) regularization. J. Vis. Commun. Image Represent 24(1), 1529–1542 (2013)
Chen, S.S., Donoho, D.L., Saunders, M.A.: Atomic decomposition by basis pursuit. SIAM J. Sci. Comput. 20(1), 33–61 (1998)
Chen, X.M.: Stability of compressed sensing for dictionaries and almost sure convergence rate for the kaczmarz algorithm. Ph.D. thesis, Vanderbilt University (2012)
Cohen, A., Dahmen, W., DeVore, R.: Compressed sensing and best k-term approximation. J Am Math Soc 22(1), 211–231 (2009)
Daubechies, I., Defrise, M., Christine, D.M.: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math 57(1), 1413–1457 (2004)
Daubechies, I., Devore, R., Fornasier, M., Gunturk, C.S.: Iteratively reweighted least squares minimization for sparse recovery. Comm. Pure Appl. Math. 63, 1–38 (2010)
Devore, R., Jawerth, B.: Image compression through wavelet transform coding. IEEE Trans. Inf. Theory 38(2), 719–746 (1992)
Donoho, D.L.: De-noising by soft-thresholding. IEEE Trans. Inf. Theory 41(3), 613–627 (1995)
Donoho, D.L.: Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289–1306 (2006)
Fan, J., Li, R.: Variable selection via nonconcave penalized likelihood and its oracle properties. J. Amer. Stat. Assoc. 96, 1348–1360 (2001)
Ghadimi, S., Lan, G.: Accelerated gradient methods for non-convex nonlinear and stochastic programming. Math. Program 156, 59–99 (2013)
Gong, P.H., Zhang, C.S., Lu, Z.S., Huang, J.H., Ye, J.P.: A general iteartive shrinkage and thresholding algorithm for non-convex regularized optimization problems. Presented at the 30th Int. Conf. Mach. Learn. (ICML), Atlanta, GA, USA (2013)
Jing, W., Meng, D., Qiao, C., Peng, Z.: Eliminating vertical stripe defects on silicon steel surface by regularization. Math. Probl. Eng. 2011, 1–13 (2011)
Lai, M.J., Xu, Y.Y., Yin, W.T.: Improved iteratively reweighted least squares for unconstrained smoothed \(l_{q}\) minimization. SIAM J. Numer. Anal. 51, 927–957 (2013)
Li, H., Lin, Z.: Accelerated proximal gradient methods for nonconvex programming. Adv. Neural Inf. Process. Syst. 28 (2015)
Li, Q., Bai, Y.Q., Yu, C.J., Yuan, Y.X.: A new piecewise quadratic approximation approach for \(l_0\) norm minimization problem. Sci. China Math. 62(1), 185–204 (2019)
Mallat, S., Zhang, Z.: Matching pursuits with time-frequency dictionaries. IEEE Trans. Signal Process. 41, 3397–3415 (1993)
Natarajan, B.K.: Sparse approximate solutions to linear systems. SIAM J. Comput. 24(2), 227–234 (1995)
Needell, D., Vershynin, R.: Signal recovery from incomplete and inaccurate measurements via regularized orthogonal matching pursuit. IEEE J. Sel. Topics Signal Process. 4, 310–316 (2010)
Nesterov, Y.: A method for unconstrained convex minimization problem with the rate of convergence \(\cal{O} (1/k^2)\). Doklady AN SSSR 269, 545–547 (1983)
Nesterov, Y.: Smoothing minimization of non-smooth functions. Math. Program 103, 127–152 (2005)
Rakotomamonjy, A., Flamary, R., Gasso, G., Canu, S.: lp-lq penalty for sparse linear and sparse multiple kernel multitask learning. IEEE Trans. Neural Netw. 22, 1307–1320 (2011)
Tibshiranit, R.: Regression shrinkage and selection via the lasso. J. Royal Stat. Soc. Ser. B 58(1), 267–288 (1996)
Tran, H., Webster, C.: A class of null space conditions for sparse recovery via nonconvex, non-separable minimizations. Results Appl Math 3, 100011 (2019)
Tropp, J.A., Gilbert, A.C.: Signal recovery from partial information via orthogonal matching pursuit. IEEE Trans. Inf. Theor. 53, 4655–4666 (2007)
Tseng, P.: On accelerated proximal gradient methods for convex-concave optimization. SIAM J Optim (2008)
Wen, B., Chen, X., Pong, T.K.: Linear convergence of proximal gradient algorithm with extrapolation for a class of nonconvex nonsmooth minimization problems. Siam J Optim 27(1), 124–145 (2017)
Xu, Z.B.: Data modeling: visual psychology approach and \(l_{1/2}\) regularization theory. Proc. Int. Congr. Math 4, 3151–3184 (2010)
Xu, Z.B., Chang, X.Y., Xu, F.M., Zhang, H.: \(l_{1/2}\) regularization: a thresholding representation theory and a fast solver. IEEE Trans. Neural Netw. Learn. Syst. 23(7), 1013–1027 (2012)
Xu, Z.B., Guo, H.L., Wang, Y., Zhang, H.: The representation of \(l_{1/2}\) regularizer among \(l_{q}, (0<q<1)\) regularizer: An experimental study based on phase diagram. Acta Autom. Sin. 38, 1225–1228 (2012)
Yang, A.Y., Ganesh, A., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 210–227 (2009)
Yang, A.Y., Ganesh, A., Zhou, Z.H., Sastry, S.S., Ma, Y.: Fast \(l_{1}\)-minimization algorithms for robust face recognition. IEEE Trans. Image Process. 22, 3234–3246 (2013)
Yin, P.H., Lou, Y.F., He, Q., Xin, J.: Minimization of \(l_{1-2}\) for compressed sensing. SIAM J. Sci. Comput. 37, 536–563 (2015)
Zeng, J., Xu, Z., Zhang, B., Hong, W., Wu, Y.: Accelerated \(l_{1/2}\) regularization based sar imaging via bcr and reduced newton skills. Signal Process. 93(7), 1831–1844 (2013)
Zeng, J.S., Jian, F., Xu, Z.B.: Sparse sar imaging based on \(l_{1/2}\) regularization. Sci. China Inf. Sci. 55(8), 1755–1775 (2012)
Zeng, J.S., Lin, S.B., Wang, Y., Xu, Z.B.: \(l_{1/2}\) regularization: convergence of iterative half thresholding algorithm. IEEE Signal Process. 62(9), 2317–2329 (2014)
Zeng, J.S., Lin, S.B., Xu, Z.B.: Sparse regularization: convergence of iterative jumping thresholding algorithm. IEEE Signal Process. 64, 5106–5118 (2014)
Zhang, C.H.: Nearly unbiaised variable selection under minimax concave penalty. Ann. Stat. 38, 894–942 (2010)
Acknowledgements
We thank the editors and the anonymous reviewers for their valuable comments and suggestions. This research was supported by the National Natural Science Foundations of China (Grants No. 11901382, 12101247, 11771275, 11971302) and the Shanghai Chenguang Project (Grants No. 19CG67).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, Q., Zhang, W., Bai, Y. et al. A non-convex piecewise quadratic approximation of \(\ell _{0}\) regularization: theory and accelerated algorithm. J Glob Optim 86, 323–353 (2023). https://doi.org/10.1007/s10898-022-01257-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10898-022-01257-6
Keywords
- Iterative thresholding algorithm
- Exact recovery
- Sparsity optimization
- Non-convex approximation
- Accelerated gradient algorithm