predict_ordinal {TensorComplete}

Predict ordinal-valued tensor entries from the cumulative logistic model.

Description

Predict ordinal-valued tensor entries given latent parameters and a type of estimations.

Usage

predict_ordinal(theta,omega,type = c("mode","mean","median"))

Arguments

theta

A continuous-valued tensor (latent parameters).

omega

The cut-off points.

type

Type of estimations:

"mode" specifies argmax based label estimation.

"mean" specifies mean based label estimation.

"median" specifies median based label estimation.

Value

A predicted ordinal-valued tensor given latent parameters and a type of estimations.

References

C. Lee and M. Wang. Tensor denoising and completion based on ordinal observations. International Conference on Machine Learning (ICML), 2020.

Examples

indices <- c(10,20,30)
arr <- array(runif(prod(indices),-2,2),dim = indices)
b <- c(-1.5,0,1.5)
r_predict <- predict_ordinal(arr,b,type = "mode");r_predict