One-bit-matching theorem for ICA, convex-concave programming on polyhedral set, and distribution approximation for combinatorics

Neural Computation

Volumn 19, Issue 2, 2007, Pages 546-569

  Xu, Lei ^a  

^a CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 33847287742     PISSN: 08997667     EISSN: 1530888X     Source Type: Journal    
DOI: 10.1162/neco.2007.19.2.546     Document Type: Article

References (28)

1. Amari, S., Chen, T.-P., & Cichocki, A. (1997). Stability analysis of adaptive blind source separation. Neural Networks, 10, 1345-1351.
2. Amari, S. I., Cichocki, A., & Yang, H. (1996). A new learning algorithm for blind separation of sources. In D. Toureteky, M. Mozer, & M. Hasselmo (Eds.), Advances in neural information processing, 8 (pp. 757-763). Cambridge, MA: MIT Press.
3. Bazaraa, M. S., Sherall, H. D., & Shetty, C. M. (1993). Nonlinear programming: Theory and algorithms. New York: Wiley.
4. Bell, A., & Sejnowski, T. (1995). An information-maximization approach to blind separation and blind deconvolution. Neural Computation, 7, 1129-1159.
5. Cardoso, J.-F. (1998). Blind signal separation: Statistical principles. Proc. IEEE, 86(10), 2009-2025.
6. Cheung, C. C., & Xu, L. (2000). Some global and local convergence analysis on the information-theoretic independent component analysis approach. Neurocomputing, 30, 79-102.
7. Comon, P. (1994). Independent component analysis: A new concept? Signal Processing, 36, 267-314.
8. Delfosse, N., & Loubation, P. (1995). Adaptive blind separation of independent sources: A deflation approach. Signal Processing, 45, 59-83.
9. Edelman, A., Arias, T. A., & Smith, S. T. (1998). The geometry of algorithms with orthogonality constraints. SIAM J. Matrix Anal. Appl., 20, 303-353.
10. Everson, R., & Roberts, S. (1999). Independent component analysis: A flexible nonlinearity and decorrelating manifold approach. Neural Computation, 11, 1957-1983.
11. Girolami, M. (1998). An alternative perspective on adaptive independent component analysis algorithms. Neural Computation, 10, 2103-2114.
12. Hopfield, J. J., & Tank, D. W. (1985). Neural computation of decisions in optimization problems. Biological Cybernetics, 52, 141-152.
13. Hyvarinen, A., Karhunen, J., & Oja, A. (2001), Independent component analysis. New York: Wiley.
14. Lee, T. W., Girolami, M., & Sejnowski, T. J. (1999). Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources. Neural Computation, 11, 417-441.
15. Liu, Z. Y., Chiu, K. C., & Xu, L. (2004). One-bit-matching conjecture for independent component analysis. Neural Computation, 16, 383-399.
16. Moreau, E., & Macchi, O. (1996). High order contrasts for self-adaptive source separation. International Journal of Adaptive Control and Signal Processing, 10, 1996.
17. Pearlmutter, B. A., & Parra, L. C. (1996). A context-sensitive genaralization of ICA. In Proc. of Int. Conf. on Neural Information Processing, 151-157. Hong Kong: Springer-Verlag.
18. Tong, L., Inouye, Y., & Liu, R. (1993). Waveform-preserving blind estimation of multiple independent sources. Signal Processing, 41, 2461-2470.
19. Welling, M., & Weber, M. (2001). A constrained EM algorithm for independent component analysis. Neural Computation, 13, 677-689.
20. Xu, L. (1994). Combinatorial optimization neural nets based on a hybrid of Lagrange and transformation approaches. In Proc. of World Congress on Neural Networks (pp. 399-404). San Diego, CA.
21. Xu, L., (1995). On the hybrid LT combinatorial optimization: New U-shape barrier, sigmoid activation, least leaking energy and maximum entropy. In Proc. of Intl. Conf. on Neural Information Processing (pp. 309-312). Beijing, China.
22. Xu, L. (1997). Bayesian ying-yang learning-based ICA models. In Proc. 1997 IEEE Signal Processing Soc. Workshop on Neural Networks for Signal Processing VII (pp. 476-485). Piscataway, NJ: IEEE.
23. Xu, L. (2003). Distribution approximation, combinatorial optimization, and Lagrange-barrier. In Proc. of International Joint Conference on Neural Networks 2003 (pp. 2354-2359). Piscataway, NJ: IEEE.
24. Xu, L. (2005). One-bit-matching ICA theorem, convex-Concave programming, and Combinatorial optimization. In Advances in neural networks (pp. 5-20). Berlin: Springer-Verlag.
25. Xu, L., Cheung, C. C., & Amari, S. I. (1998a). Further results on nonlinearity and separtion capability of a liner mixture ICA method and learned LPM. In C. Fyfe (Ed.), Proceedings of the International ICSC Workshop on Independence and Artificial Neural Networks (pp. 39-44). Tenerife, Spain.
26. Xu, L., Cheung, C. C., & Amari, S. I. (1998b). Learned parametric mixture based ICA algorithm. Neurocomputing, 22, 69-80.
27. Xu, L., Cheung, C. C., Yang, H. H., & Amari, S. I. (1997). Independent component analysis by the information-theoretic approach with mixture of density. In Proc. of 1997 IEEE-INNS International Joint Conference on Neural Networks (Vol. 3, pp. 1821-1826). Piscataway, NJ: IEEE.
28. Xu, L., Yang, H. H., & Amari, S. I. (1996, April). Signal source separation by mixtures: Accumulative distribution functions or mixture of bell-shape density distribution functions. Paper presented at the Frontier Forum, Institute of Physical and Chemical Research, Japan.