imfil: Minimization of noisy functions subject to explicit bound...
In rImfil: An R Implementation of Implicit filtering algorithm

Description Usage Arguments Details Value Author(s) References Examples

This is an implementation of Kelly's Implicit filtering algorithm for minimizing functions under contrained and bounded space.

1	imfil(x0, fn, budget, bounds, options = imfil_optset())

`x0`	Initial iterate
`fn`	Objective function
`budget`	maximum cost
`bounds`	The interval c(low, high) for x.
`options`	options for the function. The defaults are set by imfil_optset()

Implicit filtering solves bounded constrained optimization problems, where the goal is to minimize the objective function f subject to the condition that x remains in the feasible region. Implicit filtering is a sampling method. The optimization is controlled only by evaluating f at a cluster of points in the sample space. That evaluation determines the next cluster.

`x`	estimated minimizer.
`histout`	iteration history. Updated after each nonlinear iteration.
`complete_history`	complete evaluation history

Converted by Abhirup Mallik and Hans Borchers from Matlab Code by C.T. Kelly

Iterative Methods for Optimization, by C. T. Kelly

## Not run: 
fn <- f_easy
bounds <- matrix(c(-1,-1,1,1),2,2)
budget <- 40
x0 <- matrix(c(0.5,0.5))
results <- imfil(x0, fn, budget, bounds, options = imfil_optset())

## End(Not run)