approx_grad

Computes finite-difference approximation of gradient given input of arguments
x and function fn

internal

Implements Lagrangian multiplier smoothing splines for flexible
nonparametric regression and function estimation. Provides tools for fitting,
prediction, and inference using a constrained optimization approach to
enforce smoothness.
Supports generalized linear models, Weibull accelerated failure time (AFT) models,
quadratic programming problems, and customizable arbitrary correlation structures.
Options for fitting in parallel are provided. The method builds upon the framework described
by Ezhov et al. (2018) <doi:10.1515/jag-2017-0029> using Lagrangian multipliers
to fit cubic splines. For more information on correlation structure estimation,
see Searle et al. (2009) <ISBN:978-0470009598>. For quadratic programming and
constrained optimization in general, see Nocedal & Wright (2006) <doi:10.1007/978-0-387-40065-5>.
For a comprehensive background on smoothing splines, see Wahba (1990)
<doi:10.1137/1.9781611970128> and Wood (2006) <ISBN:978-1584884743>
"Generalized Additive Models: An Introduction with R".

Matthew Davis

lgspline

Lagrangian Multiplier Smoothing Splines for Smooth Function
Estimation

approx_grad function

<dl><dt>x</dt>
<dd>Numeric vector of function arguments</dd>
<dt>fn</dt>
<dd>Function returning list(objective, gradient)</dd>
<dt>eps</dt>
<dd>Numeric scalar, finite difference tolerance</dd></dl>

Arguments

Finite-difference Gradient Computer — approx_grad

<dl>

<dt>x</dt>
<dd>Numeric vector of function arguments</dd>


<dt>fn</dt>
<dd>Function returning list(objective, gradient)</dd>


<dt>eps</dt>
<dd>Numeric scalar, finite difference tolerance</dd>

</dl>

approx_grad: Finite-difference Gradient Computer

Description

Usage

Value

Arguments

Details