Xiaochun Niu

According to our database, Xiaochun Niu authored at least 8 papers between 2022 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

DISH: A Distributed Hybrid Optimization Method Leveraging System Heterogeneity.

Xiaochun Niu, Ermin Wei

IEEE Trans. Signal Process., 2024

Collaborative Learning with Shared Linear Representations: Statistical Rates and Optimal Algorithms.

Xiaochun Niu, Lili Su, Jiaming Xu, Pengkun Yang

CoRR, 2024

Exact Label Recovery in Euclidean Random Graphs.

Julia Gaudio, Charlie Guan, Xiaochun Niu, Ermin Wei

CoRR, 2024

Exact Community Recovery in the Geometric SBM.

Julia Gaudio, Xiaochun Niu, Ermin Wei

Proceedings of the 2024 ACM-SIAM Symposium on Discrete Algorithms, 2024

Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters.

Zhenyu Sun, Xiaochun Niu, Ermin Wei

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

FedHybrid: A Hybrid Federated Optimization Method for Heterogeneous Clients.

Xiaochun Niu, Ermin Wei

IEEE Trans. Signal Process., 2023

2022

DISH: A Distributed Hybrid Primal-Dual Optimization Framework to Utilize System Heterogeneity.

Xiaochun Niu, Ermin Wei

Proceedings of the 61st IEEE Conference on Decision and Control, 2022

GRAND: A Gradient-Related Ascent and Descent Algorithmic Framework for Minimax Problems.

Xiaochun Niu, Ermin Wei

Proceedings of the 58th Annual Allerton Conference on Communication, 2022