
Private Stochastic Convex Optimization: Optimal Rates in Linear Time
We study differentially private (DP) algorithms for stochastic convex op...
read it

Differentially Private Empirical Risk Minimization Revisited: Faster and More General
In this paper we study the differentially private Empirical Risk Minimiz...
read it

Differentially Private Stochastic Optimization: New Results in Convex and NonConvex Settings
We study differentially private stochastic optimization in convex and no...
read it

SA vs SAA for population Wasserstein barycenter calculation
In Machine Learning and Optimization community there are two main approa...
read it

Private Stochastic Convex Optimization: Optimal Rates in ℓ_1 Geometry
Stochastic convex optimization over an ℓ_1bounded domain is ubiquitous ...
read it

Adapting to Function Difficulty and Growth Conditions in Private Optimization
We develop algorithms for private stochastic convex optimization that ad...
read it

Recursive Optimization of Convex Risk Measures: MeanSemideviation Models
We develop and analyze stochastic subgradient methods for optimizing a n...
read it
Private Nonsmooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps
We study the differentially private Empirical Risk Minimization (ERM) and Stochastic Convex Optimization (SCO) problems for nonsmooth convex functions. We get a (nearly) optimal bound on the excess empirical risk and excess population loss with subquadratic gradient complexity. More precisely, our differentially private algorithm requires O(N^3/2/d^1/8+ N^2/d) gradient queries for optimal excess empirical risk, which is achieved with the help of subsampling and smoothing the function via convolution. This is the first subquadratic algorithm for the nonsmooth case when d is super constant. As a direct application, using the iterative localization approach of Feldman et al. <cit.>, we achieve the optimal excess population loss for stochastic convex optimization problem, with O(min{N^5/4d^1/8, N^3/2/d^1/8}) gradient queries. Our work makes progress towards resolving a question raised by Bassily et al. <cit.>, giving first algorithms for private ERM and SCO with subquadratic steps. We note that independently Asi et al. <cit.> gave other algorithms for private ERM and SCO with subquadratic steps.
READ FULL TEXT
Comments
There are no comments yet.