[R] Error in optim with method L-BFGS-B when hessian is TRUE

[Marc Girondot]

Dear members,

I fought for several days against an error I was getting with optim in 
L-BFGS-B. The error was produced because some parameters were outside 
the limits defined by upper and lower.
After investigation, the error is not produced during the optimization 
itself but during the calculation of the Hessian matrix which does not 
take into account the upper and lower bounds.
It would be nice if this was stated in the optim help within the 
L-BFGS-B method section.

Marc Girondot