A class of stochastic gradient algorithms with exponentiated error cost functions

Digital Signal Processing: A Review Journal

Volumn 19, Issue 2, 2009, Pages 201-212

  Boukis, C ^a   Mandic, D P ^b   Constantinides, A G ^b  

^a ATHENS INFORMATION TECHNOLOGY   (Greece)

^b IMPERIAL COLLEGE LONDON   (United Kingdom)

Author keywords

Adaptive filtering; Cost functions; Online optimisation; Stochastic gradient descent

Indexed keywords

ADAPTIVE FILTERING; ADAPTIVE FILTERS; COSTS; ERRORS; MEAN SQUARE ERROR; OPTIMIZATION; STOCHASTIC SYSTEMS;

CONVEX COST FUNCTION; ERROR COST FUNCTION; EXPONENTIAL DEPENDENCE; LINEAR COMBINATIONS; ONLINE OPTIMISATION; STOCHASTIC GRADIENT ALGORITHMS; STOCHASTIC GRADIENT DESCENT; STOCHASTIC GRADIENT DESCENT ALGORITHM;

COST FUNCTIONS;

EID: 58549092028     PISSN: 10512004     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.dsp.2008.11.006     Document Type: Article

References (18)

1. Benveniste A., Metivier M., and Priouret P. Adaptive Algorithms and Stochastic Approximations (1990), Springer-Verlag, New York
2. Widrow B., and Stearns S. Adaptive Signal Processing (1985), Prentice Hall
3. Bershad N. Analysis of the normalized LMS with Gaussian inputs. IEEE Trans. Acoust. Speech Signal Process. 34 4 (1986) 793-806
4. Walach E., and Widrow B. The least mean fourth (LMF) adaptive algorithm and its family. IEEE Trans. Inform. Theory 30 2 (2003) 275-283
5. Tanrikulu O., and Constantinides A. Least mean kurtosis: A novel higher-order statistics based adaptive filtering algorithm. Electron. Lett. 30 3 (1994) 189-190
6. Chambers J., Tanrikulu O., and Constantinides A. Least mean mixed-norm adaptive filtering. Electron. Lett. 30 3 (1994) 1-190
7. Chambers J., and Avlonitis A. A robust mixed-norm adaptive filter algorithm. IEEE Signal Process. Lett. 4 2 (1997) 46-48
8. D. Mandic, E. Papoulis, C. Boukis, A normalized mixed-norm adapitive filtering algorithm robust under impulsive noise interference, in: IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. VI, 2003, pp. 333-336
9. A. Barros, J. Principe, Y. Takeuchi, C. Sales, N. Ohnishi, An algorithm based in the even moments of the error, in: IEEE XIII Workshop on Neural Networks for Signal Processing, 2003, pp. 879-885
10. Kivinen J., and Warmuth M. Exponentiated gradient versus gradient descent for linear predictors. Inform. and Comput. 132 1 (1997) 1-64
11. Martin R., Sethares W., Williamson R., and Johnson Jr. C. Exploiting sparsity in adaptive filters. IEEE Trans. Signal Process. 50 8 (2002) 1883-1893
12. J. Benesty, Y. Huang, J. Chen, An exponentiated gradient adaptive algorithm for blind identification of sparse simo systems, in: IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, 2002, pp. 829-832
13. Rupp M., and Sayed A.H. A time-domain feedback analysis of filtered-error adaptive gradient algorithms. IEEE Trans. Signal Process. 44 6 (1996) 1428-1429
14. Al-Naffouri T.Y., and Sayed A.H. Adaptive filters with error nonlinearities: Mean-square analysis and optimum design. EURASIP J. Appl. Signal Process. 4 (2001) 192-205
15. Al-Naffouri T.Y., and Sayed A.H. Transient analysis of adaptive filters with error nonlinearities. IEEE Trans. Signal Process. 51 3 (2003) 653-661
16. Yousef N.R., and Sayed A.H. A unified approach to the steady-state and tracking analyses of adaptive filters. IEEE Trans. Signal Process. 49 2 (2001) 314-324
17. Van Trees L. Detection, Estimation and Modulation Theory: Part I (1968), John Wiley and Sons, New York
18. Soria-Olivas E., Calpe-Maravilla J., Guerrero-Martinez J., Martinez-Sober M., and Espi-Lopez J. An easy demonstration of the optimum value of the adaptation constant in the LMS algorithm. IEEE Trans. Educ. 41 1 (1998) 81