dot-tune_grid_search: Grid Search Initialization for Penalty Tuning

In lgspline: Lagrangian Multiplier Smoothing Splines for Smooth Function Estimation

Grid Search Initialization for Penalty Tuning

Description

Evaluates the selected tuning criterion over a grid of initial wiggle and ridge penalty values to find a good starting point for BFGS optimization.

Usage

.tune_grid_search(
  log_initial_wiggle,
  log_initial_flat,
  log_penalty_vec,
  criterion_fxn,
  env,
  include_warnings,
  parallel_grideval = TRUE,
  cl = NULL,
  ...
)

Arguments

log_initial_wiggle	Numeric vector; log-scale candidate values for the wiggle penalty.
log_initial_flat	Numeric vector; log-scale candidate values for the flat ridge penalty.
log_penalty_vec	Numeric vector; log-scale predictor/partition penalties.
criterion_fxn	Function; tuning-objective evaluation function.
env	List; tuning environment.
include_warnings	Logical; whether to print warnings on failure.
...	Additional arguments passed to criterion_fxn.

Value

Numeric vector of length 2; the best (log_wiggle, log_flat) found.

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