l0fused_c

Number of knots in the piecewise constant(breaks in the derivative), i.e., the same as s.

The maximum number of steps for the algorithm to take before termination, i.e., the same as K.max.

max_steps

This is a cpp function used for R function l0fused.

An implementation of the fast structural filtering with L0 penalty. It includes an adaptive polynomial estimator by minimizing the least squares error with constraints on the number of breaks in their (k + 1)-st discrete derivative, for a chosen integer k >= 0. It also includes generalized structure sparsity constraint, i.e., graph trend filtering. This package is implemented via the primal dual active set algorithm, which formulates estimates and residuals as primal and dual variables, and utilizes efficient active set selection strategies based on the properties of the primal and dual variables.

l0fused_c: L0 Fused Regression

Description

Usage

Arguments

Value

References