Skip to yearly menu bar Skip to main content


On User-Level Private Convex Optimization

Badih Ghazi · Pritish Kamath · Ravi Kumar · Pasin Manurangsi · Raghu Meka · Chiyuan Zhang

Exhibit Hall 1 #313
[ ]
[ PDF [ Poster


We introduce a new mechanism for stochastic convex optimization (SCO) with user-level differential privacy guarantees. The convergence rates of this mechanism are similar to those in the prior work of Levy et al. 2021 and Narayanan et al. 2022, but with two important improvements. Our mechanism does not require any smoothness assumptions on the loss. Furthermore, our bounds are also the first where the minimum number of users needed for user-level privacy has no dependence on the dimension and only a logarithmic dependence on the desired excess error. The main idea underlying the new mechanism is to show that the optimizers of strongly convex losses have low local deletion sensitivity, along with a new output perturbation method for functions with low local deletion sensitivity, which could be of independent interest.

Chat is not available.