Private Stochastic Convex Optimization: Efficient Algorithms for Non-smooth Objectives
arXiv:2002.09609
Abstract
In this paper, we revisit the problem of private stochastic convex optimization. We propose an algorithm based on noisy mirror descent, which achieves optimal rates both in terms of statistical complexity and number of queries to a first-order stochastic oracle in the regime when the privacy parameter is inversely proportional to the number of samples.
References in corpus (7)
- Rényi Divergence and Kullback-Leibler Divergence
- Renyi Differential Privacy
- Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes
- Privacy Amplification by Iteration
- Subsampled Rényi Differential Privacy and Analytical Moments Accountant
- Private Stochastic Convex Optimization with Optimal Rates
- Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits