leftMultiplyByXt: leftMultiplyByXt

In jointseg: Joint segmentation of multivariate (copy number) signals

Description

Compute X'*Y where X is the n*(n-1) design matrix for the weighted group fused Lasso, with weights defined by the vector w, and Y is any n*p matrix. The computation is done in O(np).

Usage

leftMultiplyByXt(Y, w = defaultWeights(nrow(Y)), verbose = FALSE)

Arguments

Y	A n*p matrix
w	(n-1)*1 vector of weights
verbose	A logical value: should extra information be output ? Defaults to FALSE.

Details

This implementation is derived from the MATLAB code of Vert and Bleakley: http://cbio.ensmp.fr/GFLseg.\

Contrary to getUnivStat it does not handle missing values.

Value

C	The (n-1)*p matrix equal to X'*Y

Author(s)

Morgane Pierre-Jean and Pierre Neuvial

References

Bleakley, K., & Vert, J. P. (2011). The group fused lasso for multiple change-point detection. arXiv preprint arXiv:1106.4199.\ Vert, J. P., & Bleakley, K. (2010). Fast detection of multiple change-points shared by many signals using group LARS. Advances in Neural Information Processing Systems, 23, 2343-2351.

Examples

Y <- matrix(rnorm(20), ncol=2)
C <- leftMultiplyByXt(Y)

jointseg documentation built on May 2, 2019, 5:20 p.m.