### Abstract

Although adaptive gradient algorithms are simple and relatively robust, they generally have poor performance in the absence of 'rich' excitation. In particular, it is well known that the convergence speed of the LMS algorithm deteriorates when the condition number of the input autocorrelation matrix is large. This problem has been previously addressed using weighted RLS or normalized frequency-domain algorithms. In this paper, we present a new approach that employs gradient projections in selected eigenvector sub-spaces to improve the convergence properties of LMS algorithms for colored inputs. We also introduce an efficient method to iteratively update an 'eigen subspace' of the autocorrelation matrix. The proposed algorithm is more efficient, in terms of computational complexity, than the WRLS and its convergence speed approaches that of the WRLS even for highly correlated inputs.

Original language | English (US) |
---|---|

Title of host publication | Midwest Symposium on Circuits and Systems |

Place of Publication | Piscataway, NJ, United States |

Publisher | IEEE |

Pages | 259-263 |

Number of pages | 5 |

Volume | 1 |

State | Published - 1995 |

Externally published | Yes |

Event | Proceedings of the 1995 IEEE 38th Midwest Symposium on Circuits and Systems. Part 1 (of 2) - Rio de Janeiro, Braz Duration: Aug 13 1995 → Aug 16 1995 |

### Other

Other | Proceedings of the 1995 IEEE 38th Midwest Symposium on Circuits and Systems. Part 1 (of 2) |
---|---|

City | Rio de Janeiro, Braz |

Period | 8/13/95 → 8/16/95 |

### ASJC Scopus subject areas

- Electrical and Electronic Engineering
- Electronic, Optical and Magnetic Materials

## Fingerprint Dive into the research topics of 'Gradient eigenspace projections for adaptive filtering'. Together they form a unique fingerprint.

## Cite this

*Midwest Symposium on Circuits and Systems*(Vol. 1, pp. 259-263). IEEE.