TGGLMix: Fit a tree-guided group lasso mixture model model (TGGLMix).

Description Usage Arguments Value See Also

View source: R/tggl_mixture.R

Description

Fit a tree-guided group lasso mixture model using a generalized EM algorithm. May be trained on shared or task specific feature matrices.

Usage

1
2
3
4
TGGLMix(X = NULL, task.specific.features = list(), Y, M, groups, weights,
  lambda, gam = 1, homoscedastic = FALSE, EM.max.iter = 1000,
  EM.epsilon = 1e-04, EM.verbose = 0, sample.data = FALSE,
  TGGL.mu = 1e-05, TGGL.epsilon = 1e-05, TGGL.iter = 25)

Arguments

X

N by J1 matrix of features common to all tasks.

task.specific.features

List of features which are specific to each task. Each entry contains an N by J2 matrix for one particular task (where columns are features). List has to be ordered according to the columns of Y.

Y

N by K output matrix for every task.

M

Number of Clusters.

groups

Binary V by K matrix determining group membership: Task k in group v iff groups[v,k] == 1.

weights

V dimensional vector with group weights.

lambda

Regularization parameter.

gam

(Optional) Regularization parameter for component m will be lambda times the prior for component m to the power of gam.

homoscedastic

(Optional) Force variance to be the same for all tasks in a component. Default is FALSE.

EM.max.iter

(Optional) Maximum number of iterations for EM algorithm.

EM.epsilon

(Optional) Desired accuracy. Algorithm will terminate if change in penalized negative log-likelihood drops below EM.epsilon.

EM.verbose

(Optional) Integer in 0,1,2. verbose = 0: No output. verbose = 1: Print summary at the end of the optimization. verbose = 2: Print progress during optimization.

sample.data

(Optional) Sample data according to posterior probability or not.

TGGL.mu

(Optional) Mu parameter for TGGL.

TGGL.epsilon

(Optional) Epsilon parameter for TGGL.

TGGL.iter

(Optional) Initial number of iterations for TGGL. Will be increased incrementally to ensure convergence. When the number of samples is much larger than the dimensionalty, it can be beneficial to use a large initial number of iterations for TGGL. This is because every run of TGGL requires precomputation of multiple n-by-n matrix products.

Value

List containing

models

List of TGGL models for each component.

posterior

N by M Matrix containing posterior probabilities.

prior

Vector with prior probabilities for each component.

sigmas

M by K Matrix with standard deviations for each component.

obj

Penalized negative log-likelihood (final objective value).

loglik

Likelihood for training data.

groups

groups argument.

weights

weights argument.

lambda

lambda argument.

See Also

TreeGuidedGroupLasso


tohein/linearMTL documentation built on May 17, 2019, 8:22 a.m.