compute_G_eigen: Compute Eigenvalues and Related Matrices for G

In lgspline: Lagrangian Multiplier Smoothing Splines for Smooth Function Estimation

Compute Eigenvalues and Related Matrices for G

Description

Computes partition-wise inverse-information matrices and their matrix square roots from the penalized information matrix via eigendecomposition.

Computes partition-wise inverse-information matrices and their matrix square roots from the penalized information matrix via eigendecomposition.

Usage

compute_G_eigen(
  X_gram,
  Lambda,
  K,
  parallel,
  cl,
  chunk_size,
  num_chunks,
  rem_chunks,
  family,
  unique_penalty_per_partition,
  L_partition_list,
  keep_G = TRUE,
  schur_corrections
)

compute_G_eigen(
  X_gram,
  Lambda,
  K,
  parallel,
  cl,
  chunk_size,
  num_chunks,
  rem_chunks,
  family,
  unique_penalty_per_partition,
  L_partition_list,
  keep_G = TRUE,
  schur_corrections
)

Arguments

X_gram	List of Gram matrices X_k^T W_k X_k by partition.
Lambda	Penalty matrix \Lambda (shared across partitions).
K	Integer; number of interior knots (partitions = K+1).
parallel	Logical; use parallel processing across partitions.
cl	Cluster object from parallel::makeCluster.
chunk_size, num_chunks, rem_chunks	Partition distribution parameters.
family	GLM family object.
unique_penalty_per_partition	Logical; if TRUE, add partition-specific penalties from L_partition_list.
L_partition_list	List of partition-specific penalty matrices.
keep_G	Logical; if TRUE, return the full G matrix.
schur_corrections	List of Schur complement correction matrices.

Value

A list with components G (or NULL blocks when keep_G = FALSE), Ghalf, and optionally GhalfInv.

A list with components G (or NULL blocks when keep_G = FALSE), Ghalf, and optionally GhalfInv.

lgspline documentation built on May 8, 2026, 5:07 p.m.