30
3

Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions

Abstract

We study the problem of differentially private stochastic convex optimization (DP-SCO) with heavy-tailed gradients, where we assume a kthk^{\text{th}}-moment bound on the Lipschitz constants of sample functions rather than a uniform bound. We propose a new reduction-based approach that enables us to obtain the first optimal rates (up to logarithmic factors) in the heavy-tailed setting, achieving error G21n+Gk(dnϵ)11kG_2 \cdot \frac 1 {\sqrt n} + G_k \cdot (\frac{\sqrt d}{n\epsilon})^{1 - \frac 1 k} under (ϵ,δ)(\epsilon, \delta)-approximate differential privacy, up to a mild polylog(1δ)\textup{polylog}(\frac{1}{\delta}) factor, where G22G_2^2 and GkkG_k^k are the 2nd2^{\text{nd}} and kthk^{\text{th}} moment bounds on sample Lipschitz constants, nearly-matching a lower bound of [Lowy and Razaviyayn 2023]. We further give a suite of private algorithms in the heavy-tailed setting which improve upon our basic result under additional assumptions, including an optimal algorithm under a known-Lipschitz constant assumption, a near-linear time algorithm for smooth functions, and an optimal linear time algorithm for smooth generalized linear models.

View on arXiv
Comments on this paper