Archives of Acoustics, 41, 4, pp. 731–739, 2016

Stability Conditions for the Leaky LMS Algorithm Based on Control Theory Analysis

Dariusz BISMOR
Silesian University of Technology

Silesian University of Technology

The Least Mean Squares (LMS) algorithm and its variants are currently the most frequently used adaptation algorithms; therefore, it is desirable to understand them thoroughly from both theoretical and practical points of view. One of the main aspects studied in the literature is the influence of the step size on stability or convergence of LMS-based algorithms. Different publications provide different stability upper bounds, but a lower bound is always set to zero. However, they are mostly based on statistical analysis. In this paper we show by means of control theoretic analysis confirmed by simulations that for the leaky LMS algorithm, a small negative step size is allowed. Moreover, the control theoretic approach alows to minimize the number of assumptions necessary to prove the new condition. Thus, although a positive step size is fully justified for practical applications since it reduces the mean-square error, knowledge about an allowed small negative step size is important from a cognitive point of view, and can be used on purpose in sophisticated tuning scenarios, e.g., in multiband processing.
Keywords: adaptive filtering; leaky LMS; stability; nagative step size; identification; adaptive line enhancer; active noise control.
Full Text: PDF


Bismor D. (2015), Extension of LMS stability condition over a wide set of signals. International Journal of Adaptive Control and Signal Processing, 29, 5, 653–670.

Bismor D., Czyz K., Ogonowski Z. (2016), Review and comparison of variable step-size LMS algorithms, International Journal of Acoustics and Vibration, 21, 1, 24–39.

Bubnicki Z. (2005), Modern Control Theory. Springer-Verlag, Berlin.

Elliott S., Stothers I., Nelson P. (1987), A multiple error lms algorithm and its application to the active control of sound and vibration. Acoustics, IEEE Transactions on Speech and Signal Processing, 35, 10, 1423–1434.

Gardner WA. (1984), Learning characteristics of stochastic-gradient-descent algorithms: A general study, analysis and critique. Signal Processing, 6, 113–133.

Haykin S. (2002), Adaptive Filter Theory, Fourth Edition. Prentice Hall, New York.

Kaczorek T. (1993), Control and System Theory. Wydawnictwo Naukowe PWN, Warsaw.

Kuo S.M., Morgan D.R. (1996), Active Noise Control Systems, John Wiley & Sons, New York.

Kuo S.M., Morgan D.R. (1999), Active noise control: a tutorial review, Proceedings of the IEEE, 87, 6, 943–973.

Kurczyk S., Pawelczyk M. (2014a), Active noise control using a fuzzy inference system without secondary path modeling, Archives of Acoustics, 39, 2, 243–248.

Kurczyk S., Pawelczyk M. (2014b), Active noise control without secondary path modelling – Fx-LMS with step size sign and value updated using the artificial intelligence, [in:] Proceedings of the Forum Acusticum 2014, Kraków.

Latos M., Pawelczyk M. (2010), Adaptive algorithms for enhancement of speech subject to a high-level noise, Archives of Acoustics, 35, 2, 203–212.

Ławryńczuk M. (2009), Efficient nonlinear predictive control based on structured neural models, International Journal of Applied Mathematics and Computer Science, 19, 2, 233–246.

Lin J., Varaiya P.P. (1967), Bounded-input bounded-output stability of nonlinear time-varying discrete control systems, IEEE Transactions on Automatic Control, 12, 4, 423–427.

Maliński L. (2012), The evaluation of saturation level for SMSE cost function in identification of elementary bilinear time-series model, [in:] 17th International Conference on Methods and Models in Automation and Robotics, MMAR 2012, pp. 234–239.

Mayyas K., Aboulnasr T. (1997), Leaky LMS algorithm: MSE analysis for Gaussian data, IEEE Transactions on Signal Processing, 45, 4, 927–934.

Nascimento V.H., Sayed A.H. (1999), Unbiased and stable leakage-based adaptive filters, IEEE Transactions on Signal Processing, 47, 12, 3261–3276.

Sethares W.A., Lawrence D.A., Johnson C.R., Bitmead R.R. (1986), Parameter drift in LMS adaptive filters. IEEE Transactions on Acoustics, Speech and Signal Processing, 34, 4, 868–879.

Wrona S., Pawelczyk M. (2013), Controllability-oriented placement of actuators for active noise-vibration control of flexible structures using memetic algorithms, Archives of Acoustics, 38, 4, 529–536.

Zames G. (1966), On the input-output stability of time-varying nonlinear feedback systems Part one: Conditions derived using concepts of loop gain, conicity, and positivit,. IEEE Transactions on Automatic Control, 11, 2, 228–238.

DOI: 10.1515/aoa-2016-0070

Copyright © Polish Academy of Sciences & Institute of Fundamental Technological Research (IPPT PAN)