robpca {pbdML} | R Documentation |
The optimization problem is solved by an alternating directions technique.
robpca(M, delta = 1e-07, maxiter = 1000)
M |
The input data, stored as a numeric matrix or ddmatrix. |
delta |
Numeric termination criteria. A smaller (closer to 0) value will require more iterations. See the summary following the Algorithm 1 listing in the referenced paper for details. |
maxiter |
Maximum number of iterations. Should at least be a few hundred. |
Implementation of the robust pca algorithm.
Drew Schmidt
Candes, E.J., Li, X., Ma, Y. and Wright, J., 2011. Robust principal component analysis?. Journal of the ACM (JACM), 58(3), p.11.
## Not run: m = 10 n = 3 M = matrix(rnorm(m*n), m) robsvd(M) ## End(Not run)