create.solve_equi {knockoff}

Optimization for equi-correlated fixed-X and Gaussian knockoffs

Description

This function solves a very simple optimization problem needed to create fixed-X and Gaussian SDP knockoffs on the full the covariance matrix. This may be significantly less powerful than create.solve_sdp.

Usage

create.solve_equi(Sigma)

Arguments

Sigma

positive-definite p-by-p covariance matrix.

Details

Computes the closed-form solution to the semidefinite programming problem:

\mathrm{maximize} \; s \quad \mathrm{subject} \; \mathrm{to:} \; 0 \leq s \leq 1, \; 2\Sigma - sI \geq 0

used to generate equi-correlated knockoffs.

The closed form-solution to this problem is s = 2\lambda_{\mathrm{min}}(\Sigma) \land 1.

Value

The solution s to the optimization problem defined above.

See Also

Other optimization: create.solve_asdp(), create.solve_sdp()