High temporal resolution estimators through reduced rank periodograms.
The kernel associated with positive estimators including the periodograms are expressed as a linear combination of separable kernels, each defines a smoothed Pseudo Wigner distribution (SPWD). This is achieved by applying the singular value decomposition to the 2-D kernel matrix in time and lag variables. The SPWD corresponding to the maxim singular value is considered the rank one kernel estimator which is the closest to the full rank kernel periodogram. Error bounds are derived and simulations are performed to demonstrate the effect of limiting the decomposition of the kernel matrix to dominant singular values.
|Main Author:||Amin, Moeness G.|