
The authors propose the Approximate Sample Perturbation (ASAP) algorithm, which leverages an MCMC sampler to maintain pure differential privacy (DP) and pure Gaussian DP guarantees, while achieving the optimal utility rates for strongly convex and smooth losses in nearly linear time.


coremsg

efficient-mcmc-sampling-for-private-learning-with-optimal-utility-under-pure-and-gaussian-differential-privacy


Efficient MCMC Sampling for Private Learning with Optimal Utility under Pure and Gaussian Differential Privacy
