A simple numerical method based simultaneous stochastic perturbation for estimation of high dimensional matrices
- 61 Downloads
We describe a simple algorithm for estimating the elements of a matrix as well as its decomposition under the condition that only the product of this matrix with a vector is accessible. The algorithm is based on application of the stochastic simultaneous perturbation method. Theoretical results on the convergence of the proposed algorithm are proven. Numerical experiments are presented to show the efficiency of the proposed algorithm.
KeywordsNumerical differentiation Stochastic simultaneous perturbation Matrix decomposition Singular value decomposition Parameter estimation Data assimilation
The authors would like to thank the anonymous reviewers for their valuable comments and suggestions to improve the quality of the paper.
- Bai, J., & Shi, S. (2011). Estimating high dimensional covariance matrices and its applications. Annals of Economics and Finances, 12–2, 199–215.Google Scholar
- Daley, R. (1991). Atmospheric data analysis. New York: Cambridge University Press.Google Scholar
- Hoang, H. S., & Baraille, R. (2017b). A comparison study on performance of an adaptive filter with other estimation methods for state estimation in high-dimensional system, chapter 2. In T. Hokimoto (Ed.), Advances in statistical methodologies and their application to real problems, Chapter 2 (pp. 29–52). Chennai: Intech.Google Scholar
- Kailath, T. (1991). From Kalman filtering to innovations. In A. C. Antoulas (Ed.), Martingales, scattering and other nice things, mathematical system theory (pp. 55–88). Heidelberg: Springer.Google Scholar
- Salimpour, Y., & Soltanian-Zadeh, H. (2009). Particle filtering of point processes observation with application on the modeling of visual cortex neural spiking activity. In 4th International IEEE/EMBS conference on neural engineering, NER09 (pp. 718–721).Google Scholar
- Simon, D. (2001). Kalman filtering. Embedded systems programming, 16(6), 72–79.Google Scholar