l1spectral-package: Description of the package
In l1spectral: An L1-Version of the Spectral Clustering

Description Details Author(s) References See Also Examples

Provides an l1-version of the spectral clustering algorithm devoted to robustly clustering highly perturbed graphs using l1-penalty. This algorithm is described with more details in the preprint C. Champion, M. Champion, M. Blazère, R. Burcelin and J.M. Loubes, "l1-spectral clustering algorithm: a spectral clustering method using l1-regularization" (2022).

l1-spectral clustering is an l1-penalized version of the spectral clustering algorithm, which aims at robustly detecting cluster structure of perturbed graphs by promoting sparse eigenbases solutions of specific l1-minimization problems.

The DESCRIPTION file: This package was not yet installed at build time.

Camille Champion [aut], Magali Champion [aut, cre]

C. Champion, M. Champion, M. Blazère, R. Burcelin, J.M. Loubes, l1-spectral clustering algorithm: a robust spectral clustering using Lasso regularization, Preprint (2021).

l1_spectralclustering

 #####################################################
 # Performing the l1-spectral clustering on the graph
 #####################################################

 data(ToyData)

 # if desired, the number of clusters and representative elements can be provided,
 # otherwise remove
 results2 <- l1_spectralclustering(A = ToyData$A_hat, pen = "lasso")
 results2$comm

 # when desired, the number of clusters and representative elements can also be provided
 results2 <- l1_spectralclustering(A = ToyData$A_hat, pen = "lasso",
              k=2, elements = c(1,4))