activity
20192026
most citedInput Perturbation: A New Paradigm between Central and Local Differential Privacy

10 citations · 11 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2022★ 1 cited

Sharper Utility Bounds for Differentially Private Models

Yilin Kang, Yong Liu, Jian Li +1

In this paper, by introducing Generalized Bernstein condition, we propose the first high probability excess population risk bound for dif…

cs.LG2022

Stability and Generalization of Differentially Private Minimax Problems

Yilin Kang, Yong Liu, Jian Li +1

In the field of machine learning, many problems can be formulated as the minimax problem, including reinforcement learning, generative adversarial networks, to just name a few. So…

cs.LG2021

Towards Sharper Utility Bounds for Differentially Private Pairwise Learning

Yilin Kang, Yong Liu, Jian Li +1

Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of sam…

cs.LG2020★ 10 cited

Input Perturbation: A New Paradigm between Central and Local Differential Privacy

Yilin Kang, Yong Liu, Ben Niu +3

Traditionally, there are two models on differential privacy: the central model and the local model. The central model focuses on the machine learning model and the local model focu…

cs.LG2020

Data Heterogeneity Differential Privacy: From Theory to Algorithm

Yilin Kang, Jian Li, Yong Liu +1

Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP). In this paper, we first give sharper exce…

cs.LG2019

Weighted Distributed Differential Privacy ERM: Convex and Non-convex

Yilin Kang, Yong Liu, Weiping Wang

Distributed machine learning is an approach allowing different parties to learn a model over all data sets without disclosing their own data. In this paper, we propose a weighted d…