GSP_PYRAMID_ANALYSIS - Compute the graph pyramid transform coefficients

Usage

[coarse_approximations,prediction_errors]=gsp_pyramid_analysis(Gs,signal,num_levels);
[coarse_approximations,prediction_errors]=gsp_pyramid_analysis(Gs,signal,num_levels,param);

Input parameters

`Gs`	A multiresolution sequence of graph structures, including the idx parameters tracking the subsampling pattern.
`signal`	Graph signal to analyze.
`num_levels`	Number of levels in the pyramid transform.

Output parameters

`coarse_approximations`
	Cell array with the coarse approximations at each level.
`prediction_errors`
	Cell array with the prediction errors at each level.

Description

'gsp_pyramid_analysis(Gs,signal,num_levels)' computes the graph pyramid transform coefficients of a signal \(f\).

param is a structure containing optional arguments including

param.regularize_epsilon : Interpolation parameter.
param.h_filters : A cell array of graph spectral filters. If just one filter is included, it is used at every level of the pyramid. Default

\begin{equation*} h(x) = \frac{0.5}{0.5+x} \end{equation*}

Please read the documentation of gsp_filter_analysis for other optional arguments.

Demo: gsp_demo_pyramid

References:

D. I. Shuman, M. J. Faraji, and P. Vandergheynst. A framework for multiscale transforms on graphs. arXiv preprint arXiv:1308.4942, 2013.