Timezone: »

 
Differentially Private Hamiltonian Monte Carlo
Ossi Räisä · Antti Koskela · Antti Honkela

We present DP-HMC, a variant of Hamiltonian Monte Carlo (HMC) that is differentially private (DP). We use the penalty algorithm of Yildirim et al. to make the acceptance test private, and add Gaussian noise to the gradients of the target distribution to make the HMC proposal private. Our main contribution is showing that DP-HMC has the correct invariant distribution, and is ergodic. We also compare DP-HMC with the existing penalty algorithm, as well as DP-SGLD and DP-SGNHT.

Author Information

Ossi Räisä (University of Helsinki)
Antti Koskela (University of Helsinki)
Antti Honkela (University of Helsinki)

More from the Same Authors