SZVD_ADMM: Alternating Direction Method of Multipliers for SZVD

In accSDA: Accelerated Sparse Discriminant Analysis

Alternating Direction Method of Multipliers for SZVD

Description

Iteratively solves the problem

\min(-1/2*x^TB^Tx + γ p(y): ||x||_2 ≤q 1, DNx = y)

Usage

SZVD_ADMM(B, N, D, sols0, pen_scal, gamma, beta, tol, maxits, quiet = TRUE)

Arguments

B	Between class covariance matrix for objective (in space defined by N).
N	basis matrix for null space of covariance matrix W.
D	penalty dictionary/basis.
sols0	initial solutions sols0$x, sols0$y, sols0$z
pen_scal	penalty scaling term.
gamma	l1 regularization parameter
beta	penalty term controlling the splitting constraint.
tol	tol$abs = absolute error, tol$rel = relative error to be achieved to declare convergence of the algorithm.
maxits	maximum number of iterations of the algorithm to run.
quiet	toggles between displaying intermediate statistics.

Details

This function is used by other functions and should only be called explicitly for debugging purposes.

Value

SZVD_ADMM returns an object of class "SZVD_ADMM" including a list with the following named components

x,y,z

Iterates at termination.

its

Number of iterations required to converge.

errtol

Stopping error bound at termination

See Also

Used by: SZVDcv.

accSDA documentation built on Sept. 5, 2022, 5:05 p.m.