update_beta_MM_TF

<code>update_beta_MM_TF</code> updates beta in L2E trend filtering regression using the distance penalty

An implementation of a computational framework for performing robust structured regression with the L2 criterion
from Chi and Chi (2021+). Improvements using the majorization-minimization (MM) principle from Liu, Chi, and
Lange (2022+) added in Version 2.0.

Jocelyn Chi

Robust Structured Regression via the L2 Criterion

Xiaoqian Liu

Lisa Lin

Kenneth Lange

Eric Chi

update_beta_MM_TF function

<dl><dt>y</dt>
<dd>Response vector</dd>
<dt>X</dt>
<dd>Design matrix</dd>
<dt>beta</dt>
<dd>Initial vector of regression coefficients</dd>
<dt>tau</dt>
<dd>Initial precision estimate</dd>
<dt>D</dt>
<dd>The fusion matrix</dd>
<dt>k</dt>
<dd>The number of nonzero entries in D*beta</dd>
<dt>rho</dt>
<dd>The parameter in the proximal distance algorithm</dd>
<dt>max_iter</dt>
<dd>Maximum number of iterations</dd>
<dt>tol</dt>
<dd>Relative tolerance</dd></dl>

Arguments

Beta update in L2E trend filtering regression - MM — update_beta_MM_TF

<dl>

<dt>y</dt>
<dd>Response vector</dd>


<dt>X</dt>
<dd>Design matrix</dd>


<dt>beta</dt>
<dd>Initial vector of regression coefficients</dd>


<dt>tau</dt>
<dd>Initial precision estimate</dd>


<dt>D</dt>
<dd>The fusion matrix</dd>


<dt>k</dt>
<dd>The number of nonzero entries in D*beta</dd>


<dt>rho</dt>
<dd>The parameter in the proximal distance algorithm</dd>


<dt>max_iter</dt>
<dd>Maximum number of iterations</dd>


<dt>tol</dt>
<dd>Relative tolerance</dd>

</dl>

update_beta_MM_TF: Beta update in L2E trend filtering regression - MM

Description

Usage

Value

Arguments