Function opendp::transformations::make_sized_bounded_variance

pub fn make_sized_bounded_variance<S>(
    size: usize,
    bounds: (S::Item, S::Item),
    ddof: usize
) -> Fallible<Transformation<VectorDomain<AtomDomain<S::Item>>, AtomDomain<S::Item>, SymmetricDistance, AbsoluteDistance<S::Item>>>where
    S: UncheckedSum,
    S::Item: 'static + Float,
    AtomDomain<S::Item>: LipschitzMulFloatDomain<Atom = S::Item>,
    AbsoluteDistance<S::Item>: LipschitzMulFloatMetric<Distance = S::Item>,

Make a Transformation that computes the variance of bounded data.

This uses a restricted-sensitivity proof that takes advantage of known dataset size. Use make_clamp to bound data and make_resize to establish dataset size.

Citations

• DHK15 Differential Privacy for Social Science Inference

Arguments

• size - Number of records in input data.
• bounds - Tuple of lower and upper bounds for data in the input domain.
• ddof - Delta degrees of freedom. Set to 0 if not a sample, 1 for sample estimate.

Generics

• S - Summation algorithm to use on data type T. One of Sequential<T> or Pairwise<T>.