Best points w.r.t. non dominated sorting with hypervolume contribution.

Select best subset of points by non dominated sorting with hypervolume contribution for tie breaking. Works on an arbitrary dimension of size two or higher. Non-dominated sorting is computed with moocore::pareto_rank() and hypervolume contributions with moocore::hv_contributions(). Boundary points, i.e., points that are best in at least one objective within their front, always survive tie breaking.

Usage

nds_selection(points, n_select, ref_point = NULL, minimize = TRUE)

Arguments

points

(matrix())
Numeric matrix with each column corresponding to a point

n_select

(integer(1L))
Amount of points to select.

ref_point

(numeric())
Reference point for hypervolume.

minimize

('logical()')
Should the ranking be based on minimization? Must be of length 1 for all dimensions or of length nrow(points) for each dimension. Default is TRUE for each dimension.

Value

Vector of indices of selected points