Loading...
Please wait, while we are loading the content...
Similar Documents
Robust Iterative Fitting of Multilinear Models (2005)
| Content Provider | CiteSeerX |
|---|---|
| Author | Voroov, Sergiy A. Rong, Yue Sidiropoulos, Nicholas D. Gershman, Alex B. |
| Abstract | Abstract—Parallel factor (PARAFAC) analysis is an extension of low-rank matrix decomposition to higher way arrays, also re-ferred to as tensors. It decomposes a given array in a sum of multi-linear terms, analogous to the familiar bilinear vector outer prod-ucts that appear in matrix decomposition. PARAFAC analysis gen-eralizes and unifies common array processing models, like joint diagonalization and ESPRIT; it has found numerous applications from blind multiuser detection and multidimensional harmonic re-trieval, to clustering and nuclear magnetic resonance. The pre-vailing fitting algorithm in all these applications is based on (alter-nating) least squares, which is optimal for Gaussian noise. In many cases, however, measurement errors are far from being Gaussian. In this paper, we develop two iterative algorithms for the least ab-solute error fitting of general multilinear models. The first is based on efficient interior point methods for linear programming, em-ployed in an alternating fashion. The second is based on a weighted median filtering iteration, which is particularly appealing from a simplicity viewpoint. Both are guaranteed to converge in terms of absolute error. Performance is illustrated by means of simulations, and compared to the pertinent Cramér–Rao bounds (CRBs). Index Terms—Array signal processing, non-Gaussian noise, par-allel factor analysis, robust model fitting. I. |
| File Format | |
| Journal | IEEE Trans. on Signal Processing |
| Language | English |
| Publisher Date | 2005-01-01 |
| Access Restriction | Open |
| Subject Keyword | Multilinear Model Robust Iterative Fitting Ab-solute Error Fitting Linear Programming Multidimensional Harmonic Re-trieval Par-allel Factor Analysis Absolute Error General Multilinear Model Many Case Parafac Analysis Gen-eralizes Gaussian Noise Measurement Error Efficient Interior Point Method Familiar Bilinear Vector Matrix Decomposition Numerous Application Index Term Array Signal Processing Abstract Parallel Factor Pertinent Cram Rao Multiuser Detection Simplicity Viewpoint Multi-linear Term Non-gaussian Noise Way Array Iterative Algorithm Joint Diagonalization Low-rank Matrix Decomposition Robust Model Fitting Alternating Fashion Nuclear Magnetic Resonance Pre-vailing Fitting Algorithm Unifies Common Array Processing Model |
| Content Type | Text |
| Resource Type | Article |
