Log In Sign Up

On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data

by   Di Wang, et al.

In this paper, we consider the problem of designing Differentially Private (DP) algorithms for Stochastic Convex Optimization (SCO) on heavy-tailed data. The irregularity of such data violates some key assumptions used in almost all existing DP-SCO and DP-ERM methods, resulting in failure to provide the DP guarantees. To better understand this type of challenges, we provide in this paper a comprehensive study of DP-SCO under various settings. First, we consider the case where the loss function is strongly convex and smooth. For this case, we propose a method based on the sample-and-aggregate framework, which has an excess population risk of Õ(d^3/nϵ^4) (after omitting other factors), where n is the sample size and d is the dimensionality of the data. Then, we show that with some additional assumptions on the loss functions, it is possible to reduce the expected excess population risk to Õ( d^2/ nϵ^2 ). To lift these additional conditions, we also provide a gradient smoothing and trimming based scheme to achieve excess population risks of Õ( d^2/nϵ^2) and Õ(d^2/3/(nϵ^2)^1/3) for strongly convex and general convex loss functions, respectively, with high probability. Experiments suggest that our algorithms can effectively deal with the challenges caused by data irregularity.


page 1

page 2

page 3

page 4


Faster Rates of Differentially Private Stochastic Convex Optimization

In this paper, we revisit the problem of Differentially Private Stochast...

Efficient Private SCO for Heavy-Tailed Data via Clipping

We consider stochastic convex optimization for heavy-tailed data with th...

Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data

We study stochastic convex optimization with heavy-tailed data under the...

High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Data

As one of the most fundamental problems in machine learning, statistics ...

Differentially Private ℓ_1-norm Linear Regression with Heavy-tailed Data

We study the problem of Differentially Private Stochastic Convex Optimiz...

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization

We study differentially private (DP) algorithms for smooth stochastic mi...