fastclime.selector: A precision matrix and path selector function for fastclime
In fastclime: A Fast Solver for Parameterized LP Problems, Constrained L1 Minimization Approach to Sparse Precision Matrix Estimation and Dantzig Selector

Description Usage Arguments Details Value Note Author(s) See Also Examples

Select the precision matrix and solution path for a given parameter lambda

1	fastclime.selector(lambdamtx, icovlist, lambda)

`lambdamtx`	The sequence of regularization parameters for each column, it is a `nlambda` by `d` matrix.
`icovlist`	A `nlambda` list of `d` by `d` precision matrices as an alternative graph path (numerical path) corresponding to `lambdamtx`.
`lambda`	The user specified parameter lambda. The function will return the solution path corresponding to this value. Note `lambda` has to be larger than or equal to `lambda.min` input in fastclime.

The output from fastclime stores a list of precision matrice and a matrix of parameters. This program will select the required solution path and precision matrix for a given parameter lambda.

An object with S3 class "fastclime.selector" is returned:

`icov`	The estimated precision matrix corresponding to `lambda`.
`adaj`	The estimated graph path corresponding to `lambda`.
`sparsity`	The sparsity level of this estimated graph for this value of lambda.

The function is able to estimate the precision matrices corresponding to all lambda values ranging from 1 to lambda.min, provided a large enough nlambda is used in fastclime. The function will give a message if the program could not find the solution path corresponding to the required lamba. The user may want to incease nlambda in fastclime in order to find the required solution path.

Haotian Pang, Han Liu and Robert Vanderbei
Maintainer: Haotan Pang<hpang@princeton.edu>

fastclime and fastclime-package

#generate data
L = fastclime.generator(n = 100, d = 20)

#graph path estimation
out1 = fastclime(L$data,0.1)
out2 = fastclime.selector(out1$lambdamtx, out1$icovlist,0.2)
fastclime.plot(out2$adaj)