Drsvd: Distributed Random SVD

In FPCdpca: The FPCdpca Criterion on Distributed Principal Component Analysis

Distributed Random SVD

Description

Distributed Random SVD

Usage

Drsvd(data, K, nk, m, q, k)

Arguments

data	A numeric matrix or data frame.
K	Number of distributed nodes.
nk	Size of each subset.
m	Target dimension for random projection.
q	Number of power iterations.
k	Desired rank.

Value

A vector containing MSE values and optimal subset index.

Examples

library(rsvd)
library(matrixcalc)
K <- 20
nk <- 50
p <- 8
m <- 5
q <- 5
k <- 4
n <- K * nk
data <- matrix(rexp(n * p, 0.8), ncol = p)
Drsvd(data = data, K = K, nk = nk, m = m, q = q, k = k)

FPCdpca documentation built on June 8, 2025, 10:13 a.m.