The Objective object specifies the framework for an objective function
for numerical optimization.
An Objective object.
objective_name[character(1)]
The label for the objective function.
fixed_arguments[character()]
The name(s) of the fixed argument(s) (if any).
seconds[numeric(1)]
A time limit in seconds. Computations are interrupted
prematurely if seconds is exceeded.
No time limit if seconds = Inf (the default).
Note the limitations documented in setTimeLimit.
hide_warnings[logical(1)]
Hide warnings when evaluating the objective function?
verbose[logical(1)]
Print status messages?
npar[integer()]
The length of each target argument.
target[character()]
The argument name(s) that get optimized.
gradient_specified[logical(1)]
Whether a gradient function has been specified via $set_gradient().
hessian_specified[logical(1)]
Whether a Hessian function has been specified via $set_hessian().
new()Creates a new Objective object.
Objective$new(f, target = NULL, npar, ...)f[function]
A function to be optimized.
It is expected that f has at least one numeric argument.
Further, it is expected that the return value of f is of the
structure numeric(1), i.e. a single numeric value.
target[character()]
The argument name(s) that get optimized.
All target arguments must be numeric.
Can be NULL (default), then the first function argument is selected.
npar[integer()]
The length of each target argument, i.e., the length(s) of the
numeric vector argument(s) specified by target.
...Optionally additional function arguments that are fixed during the optimization.
set_argument()Set a function argument that remains fixed during optimization.
Objective$set_argument(..., .overwrite = TRUE, .verbose = self$verbose)...Optionally additional function arguments that are fixed during the optimization.
.overwrite[logical(1)]
Overwrite existing values?
.verbose[logical(1)]
Print status messages?
get_argument()Get a fixed function argument.
Objective$get_argument(argument_name, .verbose = self$verbose)argument_name[character(1)]
A function argument name.
.verbose[logical(1)]
Print status messages?
remove_argument()Remove a fixed function argument.
Objective$remove_argument(argument_name, .verbose = self$verbose)argument_name[character(1)]
A function argument name.
.verbose[logical(1)]
Print status messages?
set_gradient()Set a gradient function.
Objective$set_gradient(
gradient,
target = self$target,
npar = self$npar,
...,
.verbose = self$verbose
)gradient[function]
A function that computes the gradient of the objective function
f.
It is expected that gradient has the same call as f, and
that gradient returns a numeric vector of length
self$npar.
target[character()]
The argument name(s) that get optimized.
All target arguments must be numeric.
Can be NULL (default), then the first function argument is selected.
npar[integer()]
The length of each target argument, i.e., the length(s) of the
numeric vector argument(s) specified by target.
...Optionally additional function arguments that are fixed during the optimization.
.verbose[logical(1)]
Print status messages?
set_hessian()Set a Hessian function.
Objective$set_hessian(
hessian,
target = self$target,
npar = self$npar,
...,
.verbose = self$verbose
)hessian[function]
A function that computes the Hessian of the objective function
f.
It is expected that hessian has the same call as f, and
that hessian returns a numeric matrix of dimension
self$npar times self$npar.
target[character()]
The argument name(s) that get optimized.
All target arguments must be numeric.
Can be NULL (default), then the first function argument is selected.
npar[integer()]
The length of each target argument, i.e., the length(s) of the
numeric vector argument(s) specified by target.
...Optionally additional function arguments that are fixed during the optimization.
.verbose[logical(1)]
Print status messages?
evaluate()Evaluate the objective function.
Objective$evaluate(
.at,
.negate = FALSE,
.gradient_as_attribute = FALSE,
.gradient_attribute_name = "gradient",
.hessian_as_attribute = FALSE,
.hessian_attribute_name = "hessian",
...
).at[numeric()]
The values for the target argument(s), written in a single vector. (
Must be of length sum(self$npar).
.negate[logical(1)]
Negate the function return value?
.gradient_as_attribute[`logical(1)]
Add the value of the gradient function as an attribute to the output?
The attribute name is defined via the .gradient_attribute_name
argument.
Ignored if $gradient_specified is FALSE.
.gradient_attribute_name[character(1)\]\cr Only relevant if .gradient_as_attribute = TRUE`.
In that case, the attribute name for the gradient (if available).
.hessian_as_attribute[`logical(1)]
Add the value of the Hessian function as an attribute to the output?
The attribute name is defined via the .hessian_attribute_name
argument.
Ignored if $hessian_specified is FALSE.
.hessian_attribute_name[character(1)\]\cr Only relevant if .hessian_as_attribute = TRUE`.
In that case, the attribute name for the Hessian (if available).
...Optionally additional function arguments that are fixed during the optimization.
evaluate_gradient()Evaluate the gradient function.
Objective$evaluate_gradient(.at, .negate = FALSE, ...).at[numeric()]
The values for the target argument(s), written in a single vector. (
Must be of length sum(self$npar).
.negate[logical(1)]
Negate the function return value?
...Optionally additional function arguments that are fixed during the optimization.
evaluate_hessian()Evaluate the Hessian function.
Objective$evaluate_hessian(.at, .negate = FALSE, ...).at[numeric()]
The values for the target argument(s), written in a single vector. (
Must be of length sum(self$npar).
.negate[logical(1)]
Negate the function return value?
...Optionally additional function arguments that are fixed during the optimization.
clone()The objects of this class are cloneable with this method.
Objective$clone(deep = FALSE)deepWhether to make a deep clone.
### define log-likelihood function of Gaussian mixture model
llk <- function(mu, sd, lambda, data) {
sd <- exp(sd)
lambda <- plogis(lambda)
cluster_1 <- lambda * dnorm(data, mu[1], sd[1])
cluster_2 <- (1 - lambda) * dnorm(data, mu[2], sd[2])
sum(log(cluster_1 + cluster_2))
}
### optimize over the first three arguments, the 'data' argument is constant
objective <- Objective$new(
f = llk, target = c("mu", "sd", "lambda"), npar = c(2, 2, 1),
data = faithful$eruptions
)
### evaluate at 1:5 (1:2 is passed to mu, 3:4 to sd, and 5 to lambda)
objective$evaluate(1:5)
Run the code above in your browser using DataLab