On the convergence of some possibilistic clustering algorithms
- 334 Downloads
In this paper, an analysis of the convergence performance is conducted for a class of possibilistic clustering algorithms (PCAs) utilizing the Zangwill convergence theorem. It is shown that under certain conditions the iterative sequence generated by a PCA converges, at least along a subsequence, to either a local minimizer or a saddle point of the objective function of the algorithm. The convergence performance of more general PCAs is also discussed.
KeywordsFuzzy clustering Possibilistic clustering Convergence
This work was supported in part by the Shanghai Philosophy and Social Science Planning Project grant (2012BGL006), Australian Research Council Discovery Grants (DP1096218 and DP130102691) and Linkage Grants (LP100200774 and LP120100566).
- Bezdek, J. C. (1980). A Convergence theorem for the fuzzy ISODATA clustering algorithms. IEEE Transactions on Pattern Analysis and Machine Intellegence, PAMI-2(1), 1–8.Google Scholar
- Hathaway, R. J., Bezdek, J. C., & Tucker, W. T. (1987). An improved convergence theory for the fuzzy ISODATA clustering algorithms, the analysis of fuzzy information (Vol. 3, pp. 123–132). Boca Raton: CRC Press.Google Scholar
- Zangwill, W. (1969). Nolinear programming: a unified approach. Englewood Cliffs, NJ: Prentice-Hall.Google Scholar