June 27, 2024Open Access

Private Zeroth-Order Nonsmooth Nonconvex Optimization

Key Points

Key points are not available for this paper at this time.

Abstract

We introduce a new zeroth-order algorithm for private stochastic optimization on nonconvex and nonsmooth objectives. Given a dataset of size M, our algorithm ensures (, ²/2) -R\'enyi differential privacy and finds a (, ) -stationary point so long as M= (d³ + d^3/2²). This matches the optimal complexity of its non-private zeroth-order analog. Notably, although the objective is not smooth, we have privacy ``for free'' whenever d.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper

Cite This Study

Zhang et al. (Thu,) studied this question.

synapsesocial.com/papers/68e6312bb6db6435875c3ab7 https://doi.org/https://doi.org/10.48550/arxiv.2406.19579

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization2024
2Differentially Private Distributed Nonconvex Stochastic Optimization with Quantized Communication2024
3Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States2025
4How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization2024
5Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query Complexity2024

Mark Helpful

Bookmark

Relay

View Full Paper