csr | R Documentation |
Incorporates techniques in section 3.4 This step aims to reduce the computation burden when K is large, but it is not feasible when K is too large using standard R functions For example, when K = 50, k = 25, the vector 1:choose(50,25) consumes 941832.4 Gb memory, which is an astronomical number Future worke: see Boot and Nibbering (2019) Random subspace method.
csr(y, X, k, C.upper = 5000, intercept = FALSE)
y |
response variable |
X |
Predictor matrix |
k |
subset size |
C.upper |
maximum number of subsets to be combined |
intercept |
A boolean: include an intercept term or not |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.