Private ways to estimate high-dimensional functions
Researchers designed evaluators to privately approximate function values using a black-box approach.
Researchers studied the private black-box evaluation of arbitrary high-dimensional functions. The goal is to privately output an approximation to given a dataset and query access to a function .
The sensitivity of the function may be unknown or unbounded. A black-box evaluator can only query the value of over a down neighborhood of . A down neighborhood consists of subsets of obtained by removing a bounded number of elements.
The researchers designed generic black-box evaluators for both pure and approximate differential privacy. These evaluators use a reduction to high-dimensional private quasi-concave optimization (QCO). Quasi-concave optimization (QCO) is a type of optimization.
The evaluator's output is guaranteed to be in the convex hull of vectors obtained by applying on sets in a down neighborhood of with high probability. This work generalizes the result of Linder et al. [LRSS25] for real-valued function evaluation to high dimensions.
The evaluators can be applied to user-level quasi-concave and convex optimization. They may improve upon the sample-and-aggregate baseline of Nissim et al. [NRS07] by replacing multiplicative data overhead with an additive overhead.
The formulation of high dimensional black-box evaluation and high dimensional private QCO are equivalent up to a factor of the dimension. The hardest private evaluation instances arise when is a non-private quasi-concave optimizer.
Key facts
- The evaluator outputs an approximation to privately.
- The evaluator uses a down neighborhood of to query the function .
- The work generalizes the result of Linder et al. [LRSS25] to high dimensions.
- The evaluators may improve upon the sample-and-aggregate baseline of Nissim et al. [NRS07].