Improved convergence analysis of stochastic gradient adaptive filters using the sign algorithm

1987/04/01 by V. Mathews, V.J. Mathews, Sung Cho +1 · 2 citations
Engineering · Computer Science · #Advanced Adaptive Filtering Techniques #Direction-of-Arrival Estimation Techniques #Blind Source Separation Techniques

paper · doi:10.1109/tassp.1987.1165167

Abstract

Convergence analysis of stochastic gradient adaptive filters using the sign algorithm is presented in this paper. The methods of analysis currently available in literature assume that the input signals to the filter are white. This restriction is removed for Gaussian signals in our analysis. Expressions for the second moment of the coefficient vector and the steady-state error power are also derived. Simulation results are presented, and the theoretical and empirical curves show a very good match.

Citations

• Adaptive noise cancelling: Principles and applications

Cited by

• Proportionate Adaptive Filtering under Correntropy Criterion in Impulsive Noise Environments
• Adaptive polynomial filters

Related

• Non asymptotic analysis of Adaptive stochastic gradient algorithms and applications
• The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance
• Stochastic modified equations and adaptive stochastic gradient algorithms
• Convergence Rate of Stochastic Gradient Search in the Case of Multiple and Non-Isolated Minima
• On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes