collaborators

6 papers

cs.LG2025

Consistent Estimation of Numerical Distributions under Local Differential Privacy by Wavelet Expansion

Puning Zhao, Zhikun Zhang, Bo Sun +4

Distribution estimation under local differential privacy (LDP) is a fundamental and challenging task. Significant progresses have been made on categorical data. However, due to dif…

cs.LG2024

Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates

Puning Zhao, Jiafei Wu, Zhe Liu +3

We study convex optimization problems under differential privacy (DP). With heavy-tailed gradients, existing works achieve suboptimal rates. The main obstacle is that existing grad…

stat.ML2024

Learning with User-Level Local Differential Privacy

Puning Zhao, Li Shen, Rongfei Fan +4

User-level privacy is important in distributed systems. Previous research primarily focuses on the central model, while the local models have received much less attention. Under th…

cs.LG2024

Enhancing Learning with Label Differential Privacy by Vector Approximation

Puning Zhao, Rongfei Fan, Huiwen Wu +3

Label differential privacy (DP) is a framework that protects the privacy of labels in training datasets, while the feature vectors are public. Existing approaches protect the priva…

cs.LG2024

CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models

Huiwen Wu, Xiaogang Xu, Deyi Zhang +3

The success of current Large-Language Models (LLMs) hinges on extensive training data that is collected and stored centrally, called Centralized Learning (CL). However, such a coll…

cs.LG2024

A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy

Puning Zhao, Lifeng Lai, Li Shen +3

Privacy protection of users' entire contribution of samples is important in distributed systems. The most effective approach is the two-stage scheme, which finds a small interval f…