Abstract
Robust principal component pursuit (RPCP) refers to a decomposition of a data matrix into a low-rank component and a sparse component. In this work, instead of invoking a convex-relaxation model based on the nuclear norm and the \(\ell ^1\)-norm as is typically done in this context, RPCP is solved by considering a least-squares problem subject to rank and cardinality constraints. An inexact alternating minimization scheme, with guaranteed global convergence, is employed to solve the resulting constrained minimization problem. In particular, the low-rank matrix subproblem is resolved inexactly by a tailored Riemannian optimization technique, which favorably avoids singular value decompositions in full dimension. For the overall method, a corresponding \(q\)-linear convergence theory is established. The numerical experiments show that the newly proposed method compares competitively with a popular convex-relaxation based approach.
Similar content being viewed by others
Notes
This trial step is optional, which is only recommended for utility if the global minimizer tends to be accepted and can be computed at low cost. Unless otherwise specified, this step is skipped in our algorithmic development and analysis.
References
LMaFit: Low-rank matrix fitting. http://lmafit.blogs.rice.edu
Low-rank matrix recovery and completion via convex optimization. http://perception.csl.illinois.edu/matrix-rank/sample_code.html
PROPACK–Software for large and sparse SVD calculations. http://sun.stanford.edu/rmunk/PROPACK/
Statistical modeling of complex background for foreground object detection. http://perception.i2r.a-star.edu.sg/bk_model/bk_index.html
Absil, P.-A., Mahony, R., Sepulchre, R.: Optimization Algorithms on Matrix Manifolds. Princeton University Press, New Jersey (2008)
Absil, P.-A., Malick, J.: Projection-like retractions on matrix manifolds. SIAM J. Optim. 22, 135–158 (2012)
Boumal, N., Absil, P.-A., RTRMC: A Riemannian trust-region method for low-rank matrix completion. In: Advances in Neural Information Processing Systems, pp. 406–414 (2011)
Boumal, N., Mishra, B., Absil, P.-A., Sepulchre, R.: Manopt, a Matlab toolbox for optimization on manifolds. J. Mach. Learn. Res. 15, 1455–1459 (2014). http://www.manopt.org
Cai, J.F., Candès, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20, 1956–1982 (2010)
Candès, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM 58, 1–37 (2011)
Candès, E.J., Recht, B.: Exact matrix completion via convex optimization. Found. Comput. Math. 9, 717–772 (2009)
Chandrasekaran, V., Sanghavi, S., Parrilo, P.A., Willsky, A.S.: Rank-sparsity incoherence for matrix decomposition. SIAM J. Optim. 21, 572–596 (2011)
Eckart, C., Young, G.: The approximation of one matrix by another of lower rank. Psychometrika 1, 211–218 (1936)
Edelman, A., Arias, T.A., Smith, S.T.: The geometry of algorithms with orthogonality constraints. SIAM J. Matrix Anal. Appl. 20, 303–353 (1998)
Huang, P.-S., Chen, S. D., Smaragdis, P., Hasegawa-Johnson, M.: Singing-voice separation from monaural recordings using robust principal component analysis. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 57–60 (2012)
Ji, H., Huang, S., Shen, Z., Xu, Y.: Robust video restoration by joint sparse and low rank matrix approximation. SIAM J. Imaging Sci. 4, 1122–1142 (2011)
Jia, K., Chan, T.-H., Ma, Y.: Robust and practical face recognition via structured sparsity. In: Proceedings of the 12th European Conference on Computer Vision, vol. 4, pp. 331–344 (2012)
Keshavan, R.H., Montanari, A., Oh, S.: Matrix completion from a few entries. IEEE Trans. Inf. Theory 56, 2980–2998 (2010)
Keshavan, R.H., Montanari, A., Oh, S.: Matrix completion from noisy entries. J. Mach. Learn. Res. 11, 2057–2078 (2010)
Knuth, D.: Sorting and Searching. The art of computer programming, vol. 3. Addison-Wesley, Reading (1997)
Lewis, A.S., Malick, J.: Alternating projections on manifolds. Math. Oper. Res. 33, 216–234 (2008)
Li, L., Huang, W., Gu, I.Y.-H., Tian, Q.: Statistical modeling of complex backgrounds for foreground object detection. IEEE Trans. Image Process. 13, 1459–1472 (2004)
Lin, Z., Chen, M., Wu, L., Ma, Y.: The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices, Technical Report UILU-ENG-09-2215, UIUC, (2009)
Meyer, G., Bonnabel, S., Sepulchre, R.: Regression on fixed-rank positive semidefinite matrices: a Riemannian approach. J. Mach. Learn. Res. 12, 593–625 (2011)
Min, K., Zhang, Z., Wright, J., Ma, Y.: Decomposing background topics from keywords by principal component pursuit. In: Proceedings of the 19th ACM international conference on Information and knowledge management, pp. 269–278 (2010)
Ngo, T.T., Saad, Y.: Scaled gradients on Grassmann manifolds for matrix completion. Adv. Neural Inf. Process. Syst. 25, 1421–1429 (2012)
Nocedal, J., Wright, S.: Numerical Optimization, 2nd edn. Springer, New York (2006)
Seber, G.A.F.: Multivariate Observations. Wiley, Hoboken, NJ (1984)
Simonsson, L., Eldén, L.: Grassmann algorithms for low rank approximation of matrices with missing values. BIT Numer. Math. 50, 173–191 (2010)
Smith, S.T.: Geometric Optimization Methods for Adaptive Filtering, PhD thesis, Harvard University (1993)
Tao, M., Yuan, X.: Recovering low-rank and sparse components of matrices from incomplete and noisy observations. SIAM J. Optim. 21, 57–81 (2011)
Trefethen, L.N., Bau III, D.: Numerical Linear Algebra. SIAM, Philadelphia (1997)
Vandereycken, B.: Low-rank matrix completion by Riemannian optimization. SIAM J. Optim. 23, 1214–1236 (2013)
Wen, Z., Yin, W., Zhang, Y.: Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm. Math. Prog. Comput. 4, 333–361 (2012)
Zhang, Z., Ganesh, A., Liang, X., Ma, Y.: TILT: transform invariant low-rank textures. Int. J. Comput. Vis. 99, 1–24 (2012)
Acknowledgments
This research was supported by the Austrian Science Fund (FWF) through START project Y305 “Interfaces and Free Boundaries” and through SFB project F3204 “Mathematical Optimization and Applications in Biomedical Sciences”.
Author information
Authors and Affiliations
Corresponding author
Appendix: Local Convergence of an Alternating Projection Method.
Appendix: Local Convergence of an Alternating Projection Method.
Here we consider a heuristic alternating projection method for the RPCP problem. This method, which can be interpreted as an exact alternating minimizer scheme for the optimization problem (1) with \(\mu =0\), can be shortly described as follows. Given \(A^k\in \mathcal {M}\), one generates
The name “alternating projection method” is termed, since the iterative procedure (on \(\{A^k\}\)) can be expressed as
with \(\iota :A\mapsto Z-A\), and thus generalizes the classical alternating projection (where \(\iota \) is the identity map) in, e.g, [21]. The following theorem asserts the local convergence of the alternating projection method. However, we note that the global convergence for this method is not guaranteed in general.
Theorem 4.1
Given \(A^0\in \mathcal {M}\), let the sequence \(\{(A^k,B^k)\}\) be iteratively generated by formula (24). Assume that \((A^k,B^k)\) is sufficiently close to some \((A^*,B^*)\) such that \(\mathrm{rank}(A^*)=r\), \(\Vert B^*\Vert =s\), \(T_\mathcal {M}(A^*)\cap T_\mathcal {N}(B^*)=\{0\}\), and moreover
Then \(\{(A^k,B^k)\}\) converges to \((A^*,B^*)\) \(q\)-linearly at rate \(\kappa _p\); i.e.
where \(\kappa _p\in [0,1)\) is a constant (same as in Lemma 3.10) such that
for all \(\Delta \in \mathbb {R}^{m\times n}\).
Proof
We only prove the \(q\)-linear convergence on \(\{A^k\}\), as the proof for \(\{B^k\}\) is almost identical. Note that \(\mathcal {M}\) and \(\mathcal {N}\) are two smooth manifolds near \(A^*\) and \(B^*\), respectively. For the existence of a qualified constant \(\kappa _p\), we refer to Lemma 3.10(iii).
In the following, we perturb both equations in (26) with respect to \(A^*\) by an arbitrarily fixed \(\Delta \in \mathbb {R}^{m\times n}\). The perturbation of the first equation gives
Since \(A^*\) is a fixed point of the map \(\psi \) in (25), the second equation in (26) can be written as \(\psi (A^*)=P_\mathcal {M}(Z-B^*)\). Then we have
Thus, by considering \(\Delta =A^k-A^*\) and passing \(\Delta \rightarrow 0\), we conclude that
\(\square \)
Rights and permissions
About this article
Cite this article
Hintermüller, M., Wu, T. Robust Principal Component Pursuit via Inexact Alternating Minimization on Matrix Manifolds. J Math Imaging Vis 51, 361–377 (2015). https://doi.org/10.1007/s10851-014-0527-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-014-0527-y
Keywords
- Matrix decomposition
- Low-rank matrix
- Sparse matrix
- Image processing
- Alternating minimization
- Riemannian manifold
- Optimization on manifolds