Skip to yearly menu bar Skip to main content


Certified private data release for sparse Lipschitz functions

Konstantin Donhauser · Johan Lokna · Amartya Sanyal · March Boedihardjo · Robert Hönig · Fanny Yang

MR1 & MR2 - Number 84
[ ]
Thu 2 May 8 a.m. PDT — 8:30 a.m. PDT


As machine learning has become more relevant for everyday applications, a natural requirement is the protection of the privacy of the training data. When the relevant learning questions are unknown in advance, or hyper-parameter tuning plays a central role, one solution is to release a differentially private synthetic data set that leads to similar conclusions as the original training data. In this work, we introduce an algorithm that enjoys fast rates for the utility loss for sparse Lipschitz queries. Furthermore, we show how to obtain a certificate for the utility loss for a large class of algorithms.

Live content is unavailable. Log in and register to view live content