tensorsparse (version 3.0)

tbmClustering: Perform tensor clustering via tensor block model (TBM)

Description

Perform tensor clustering via tensor block model (TBM) method.

Usage

tbmClustering(
  x,
  k,
  r,
  l,
  lambda = 0,
  max.iter = 1000,
  threshold = 1e-10,
  sim.times = 1,
  trace = FALSE,
  Cs.init = NULL,
  Ds.init = NULL,
  Es.init = NULL,
  method = "L0"
)

Arguments

x

an order-3 data tensor

k

an positive integer, the numbers of clusters at mode 1

r

an positive integer, the numbers of clusters at mode 2

l

an positive integer, the numbers of clusters at mode 3

lambda

a numeric value, regularization coefficient

max.iter

a positive integer, the maximum numbers of iteration

threshold

a positive small numeric value for convergence threshold

sim.times

the number of simulation replicates when performing clustering

trace

logic value, print result per each iteration if TRUE

Cs.init

vector or NULL, initial cluster label assignment at mode 1

Ds.init

vector or NULL, initial cluster label assignment at mode 2

Es.init

vector or NULL, initial cluster label assignment at mode 3

method

two options: "L0", "L1". "L0" indicates L0 penalty, and "L1" indicates Lasso penalty

Value

a list

judgeX estimated underlying signal tensor

Cs clustering result at mode 1

Ds clustering result at mode 2

Es clustering result at mode 3

mus estimated block means

References

M. Wang and Y. Zeng, "Multiway clustering via tensoe block models". Advances in Neural Information Processing System 32 (NeurIPS), 715-725, 2019.

Examples

# NOT RUN {
x = getOrder3Tensor(20,20,20,2,2,2)$x
tbmClustering(x,2,2,2)

# }