BuildTreeHC: Construct tree for 'TreeGuidedGroupLasso' using hierarchical...

In tohein/linearMTL: Linear Models for Multi-Task Learning

Description

Compute tree and node weights from the results of applying hierarchical clustering to the (response) matrix Y.

Usage

BuildTreeHC(Y, threshold = 0.9, linkage = "complete")

Arguments

Y	N by K matrix for every task.
threshold	Threshold used for cutting nodes with high dissimilarity.
linkage	Linkage type used for hierarchical clustering.

Value

List containing

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

See Also

TreeGuidedGroupLasso, ComputeGroupWeights.

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