Abstract
Robust Principal Component Analysis is generalized to a multi-objective optimization problem, named as Multi-objective Robust Principal Component Analysis (MRPCA) in this paper. We aim to solve MRPCA via Evolutionary Algorithm. To the best knowledge of authors, this is the first attempt to use evolutionary algorithm to solve MRPCA problem, which is a high dimension convex optimization problem. Specifically, one of the popular evolutionary algorithm, NSGA-II, is tested on MRPCA problem. The curse of dimensionality is observed when the dimension of MRPCA problem increases. Since this problem is convex, which is a friendly structure, we propose a modified NSGA-II by introducing a new mutation method: ADMM (Alternating Direction Method of Multipliers) mutation. Numerical experiments show our modified NSGA-II algorithm converges much faster than the standard one.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
HV metric is not used for comparing because it has different reference point for different dimensions. Besides, the value of Hypervolume can not be compared for different dimension because of different pareto-optimal solutions set.
References
Hwang, C.L., Masud, A.S.M.: Multiple Objective Decision Making Methods and Applications. Lecture Notes in Economics and Mathematical Systems, vol. 164. Springer, Berlin (1979)
Li, K., Zhang, Q., Kwong, S., Li, M., Wang, R.: Stable matching based selection in evolutionary multiobjective optimization. IEEE Trans. Evol. Comput. 6(18), 909–923 (2014)
Li, K., Fialho, Á., Kwong, S., Zhang, Q.: Adaptive operator selection with bandits for multiobjective evolutionary algorithm based on decomposition. IEEE Trans. Evol. Comput. 1(18), 114–130 (2014)
Li, K., Kwong, S., Zhang, Q., Deb, K.: Interrelationship-based selection for decomposition multiobjective optimization. IEEE Trans. Cybern. 45, 2076–2088 (2015)
Candès, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM 58(3), 1–37 (2011)
Deb, K., Agrawal, S., Pratap, A., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Jiang, S., Zhang, J., Ong, Y., Feng, L.: Consistencies and contradictions of performance metrics in multiobjective optimization. IEEE Trans. Cybern. 44, 2391–2404 (2014)
Parikh, N., Boyd, S.: Proximal algorithms. Found. Trends Optim. 1(3), 123–231 (2014)
Sboyd, S., Boyd, N., Parikh, E., Chu, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Optim. 3(1), 1–122 (2011)
Deb, K., Agarwal, R.B.: Simulated binary crossover for continuous search space. Complex Syst. 9(2), 115–148 (1995)
Beyer, H., Deb, K.: On self-adaptive features in real-parameter evolutionary algorithm. IEEE Trans. Evol. Comput. 3(5), 250–270 (2001)
Raghuwanshi, M.M., Kakde, O.G.: Survey on multiobjective evolutionary and real coded genetic algorithms. In: Proceedings of the 8th Asia Paciffic Symposium on Intelligent and Evolutionary Systems, pp. 150–161 (2004)
Zhang, X., Tian, Y., Cheng, R., Jin, Y.: An efficient approach to non-dominated sorting for evolutionary multi-objective optimization. IEEE Trans. Evol. Comput. 19(2), 201–213 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yuan, W., Lin, N., Chen, H., Liang, X., He, M. (2015). A NSGA-II with ADMM Mutation for Solving Multi-objective Robust PCA Problem. In: Gong, M., Linqiang, P., Tao, S., Tang, K., Zhang, X. (eds) Bio-Inspired Computing -- Theories and Applications. BIC-TA 2015. Communications in Computer and Information Science, vol 562. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-49014-3_52
Download citation
DOI: https://doi.org/10.1007/978-3-662-49014-3_52
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-49013-6
Online ISBN: 978-3-662-49014-3
eBook Packages: Computer ScienceComputer Science (R0)