Backward difference numerical gradient approximation.
grback computes the backward difference approximation to the gradient of
user function userfn.
grback(par, userfn, fbase=NULL, env=optsp, ...)
par |
parameters to the user objective function userfn |
userfn |
User-supplied objective function |
fbase |
The value of the function at the parameters, else NULL. This is to save recomputing the function at this point. |
env |
Environment for scratchpad items (like |
... |
optional arguments passed to the objective function. |
| Package: | grback |
| Depends: | R (>= 2.6.1) |
| License: | GPL Version 2. |
grback returns a single vector object df which approximates the
gradient of userfn at the parameters par. The approximation is controlled by a
global value optderiveps that is set when the package is attached.
John C. Nash
cat("Example of use of grback\n")
myfn<-function(xx, shift=100){
ii<-1:length(xx)
result<-shift+sum(xx^ii)
}
xx<-c(1,2,3,4)
ii<-1:length(xx)
print(xx)
gn<-grback(xx,myfn, shift=0)
print(gn)
ga<-ii*xx^(ii-1)
cat("compare to analytic gradient:\n")
print(ga)
cat("change the step parameter to 1e-4\n")
optsp$deps <- 1e-4
gn2<-grback(xx,myfn, shift=0)
print(gn2)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.