Conference Proceedings

The bernstein mechanism: Function release under differential privacy

F Aldà, BIP Rubinstein

31st AAAI Conference on Artificial Intelligence, AAAI 2017 | Unknown | Published : 2017

Abstract

© Copyright 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. We address the problem of general function release under differential privacy, by developing a functional mechanism that applies under the weak assumptions of oracle access to target function evaluation and sensitivity. These conditions permit treatment of functions described explicitly or implicitly as algorithmic black boxes. We achieve this result by leveraging the iterated Bernstein operator for polynomial approximation of the target function, and polynomial coefficient perturbation. Under weak regularity conditions, we establish fast rates on utility measured by high-probabi..

View full abstract

Grants

Awarded by Australian Research Council


Funding Acknowledgements

This work was partially completed while F. Aida was visiting the University of Melbourne. Moreover, he acknowledges support of the DFG Research Training Group GRK 1817/1. The work of B. Rubinstein was supported by the Australian Research Council (DE160100584).