SUREthresh

Adaptive Threshold Selection Using Principle of SURE
(The irreductible variance term is not included,
 it does not change the position of the minimum).

Provides the standard operations for signal processing on graphs:
graph Fourier transform, spectral graph wavelet transform,
visualization tools. It also implements a data driven method
for graph signal denoising/regression, for details see
De Loynes, Navarro, Olivier (2019) <arxiv:1906.01882>.
The package also provides an interface to the SuiteSparse Matrix Collection,
<https://sparse.tamu.edu/>, a large and widely used set of sparse matrix
benchmarks collected from a wide range of applications.

Fabien Navarro

gasper

Graph Signal Processing

Basile de Loynes

Baptiste Olivier

SUREthresh function

<dl><dt>wcn</dt>
<dd>Noisy wavelet coefficents.</dd>
<dt>tresh</dt>
<dd>Threshold values.</dd>
<dt>diagWWt</dt>
<dd>Weights.</dd>
<dt>b</dt>
<dd>Thresholding type (b=1: soft, b=2: JS).</dd>
<dt>sigma</dt>
<dd>Sd of the noise.</dd>
<dt>hatsigma</dt>
<dd>Estimator of the sd (if any).</dd>
<dt>policy</dt>
<dd>Dependent or uniform.</dd>
<dt>keepwc</dt>
<dd>Boolean allowing to export the coefficients of the frame after thresholding (TRUE by default).</dd></dl>

Arguments

Stein's Unbiased Risk Estimate. — SUREthresh

<dl>

<dt>wcn</dt>
<dd>Noisy wavelet coefficents.</dd>


<dt>tresh</dt>
<dd>Threshold values.</dd>


<dt>diagWWt</dt>
<dd>Weights.</dd>


<dt>b</dt>
<dd>Thresholding type (b=1: soft, b=2: JS).</dd>


<dt>sigma</dt>
<dd>Sd of the noise.</dd>


<dt>hatsigma</dt>
<dd>Estimator of the sd (if any).</dd>


<dt>policy</dt>
<dd>Dependent or uniform.</dd>


<dt>keepwc</dt>
<dd>Boolean allowing to export the coefficients of the frame after thresholding (TRUE by default).</dd>

</dl>

SUREthresh: Stein's Unbiased Risk Estimate.

Description

Usage

Value

Arguments

References

See Also