The elementwise KL-divergence \(x\log(x/y) - x + y\).
KLDiv(x, y)# S4 method for KLDiv
to_numeric(object, values)
# S4 method for KLDiv
sign_from_args(object)
# S4 method for KLDiv
is_atom_convex(object)
# S4 method for KLDiv
is_atom_concave(object)
# S4 method for KLDiv
is_incr(object, idx)
# S4 method for KLDiv
is_decr(object, idx)
# S4 method for KLDiv
.grad(object, values)
# S4 method for KLDiv
.domain(object)
A list of numeric values for the arguments
An index into the atom.
to_numeric
: The KL-divergence evaluted elementwise on the input value.
sign_from_args
: The atom is positive.
is_atom_convex
: The atom is convex.
is_atom_concave
: The atom is not concave.
is_incr
: The atom is not monotonic in any argument.
is_decr
: The atom is not monotonic in any argument.
.grad
: Gives the (sub/super)gradient of the atom w.r.t. each variable
.domain
: Returns constraints describng the domain of the node