Closed a-torgovitsky closed 3 years ago
Done! I have updated the code to reflect the change. I am assigning the upper/lower bound of the confidence interval as the logical upper/lower bound when none of the candidates for the upper/lower bound satisfy the constraints of the minimization problem.
On the other hand, if the point estimate for the upper bound is Inf
, then I am going to set the upper bound of the confidence interval as Inf
(and similarly for the lower bound) as discussed in #79.
Thanks!
The upper bound should be the minimum of +Inf and the logical upper bound. For example,
which gives
should instead be
since in this case we can determine that
A.tgt * x
must be within[0,1]
.And analogously for the lower bound, of course.