On Theoretical Limits of Learning with Label Differential Privacy

P Zhao, C Ma, L Shen, S Wang, R Fan - arxiv preprint arxiv:2502.14309, 2025 - arxiv.org
Label differential privacy (DP) is designed for learning problems involving private labels and
public features. While various methods have been proposed for learning under label DP, the …

Private least absolute deviations with heavy-tailed data

D Wang, J Xu - Theoretical Computer Science, 2025 - Elsevier
We study the problem of Differentially Private Stochastic Convex Optimization (DPSCO) with
heavy-tailed data. Specifically, we focus on the problem of Least Absolute Deviations, ie, ℓ 1 …

A Stochastic Conjugate Subgradient Framework for Large-Scale Stochastic Optimization Problems

D Zhang - 2024 - search.proquest.com
Stochastic Optimization is a cornerstone of operations research, providing a framework to
solve optimization problems under uncertainty. Despite the development of numerous …