Jinhui Xu

On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data

2020 · arXiv (Cornell University)

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 …

Learning Manifold Implicitly via Explicit Heat-Kernel Learning

2020 · arXiv (Cornell University)

Manifold learning is a fundamental problem in machine learning with numerous applications. Most of the existing methods directly learn the low-dimensional embedding of the data in some high-dimensional space, and usually lack the flexibility of …

On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data

2022 · arXiv (Cornell University)

In this paper, we study the problem of PAC learning halfspaces in the non-interactive local differential privacy model (NLDP). To breach the barrier of exponential sample complexity, previous results studied a relaxed setting where the …

Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

In this paper, we study the problem of (finite sum) minimax optimization in the Differential Privacy (DP) model. Unlike most of the previous studies on the (strongly) convex-concave settings or loss functions satisfying the Polyak-Lojasiewicz …