Xiaochun (Nora) Niu

xiaochun.niu@duke.edu

I am a postdoctoral researcher in Decision Sciences at the Fuqua School of Business, Duke University, working with Prof. Jiaming Xu. I received my Ph.D. from the Department of Industrial Engineering and Management Sciences at Northwestern University, where I was advised by Prof. Ermin Wei and Prof. Julia Gaudio, and my B.S. in Mathematics from Nanjing University.

My research interests lie at the intersection of operations research, artificial intelligence, and data analytics. I am developing theoretical foundations and efficient algorithms for data-driven decision-making in large-scale stochastic and networked systems, with applications in business, engineering, and the natural sciences. My recent work has explored topics on sparse flexibility design, community detection and matching in random geometric graphs, and multi-agent learning under heterogeneity.

Google Scholar LinkedIn CV

Preprints and Publications

Working Papers

Optimality of Random Regular Graphs for Sparse Flexibility Designs
Weijia Li, Xiaochun Niu, Yehua Wei, Jiaming Xu
Working Paper, 2025+
Approximate Random Geometric Graph Matching
Xiaochun Niu, Tselil Schramm, Jiaming Xu
Working Paper, 2025+

Journal Papers

Learning with Shared Representations: Statistical Rates and Efficient Algorithms
Xiaochun Niu, Lili Su, Jiaming Xu, Pengkun Yang
Submitted, 2025+
Oral presentation at International Workshop on Federated Foundation Models (NeurIPS 2024)
Exact Label Recovery in Euclidean Random Graphs
Julia Gaudio, Charlie Guan, Xiaochun Niu, Ermin Wei
Major Revision, Annals of Applied Probability, 2025+
DISH: A Distributed Hybrid Optimization Method Leveraging System Heterogeneity
Xiaochun Niu, Ermin Wei
IEEE Transactions on Signal Processing, 2024
Extended abstract in Allerton Conference, 2022
FedHybrid: A Hybrid Federated Optimization Method for Heterogeneous Clients
Xiaochun Niu, Ermin Wei
IEEE Transactions on Signal Processing, 2023

Conference Papers

Incentive Analysis for Agent Participation in Federated Learning
Lihui Yi, Xiaochun Niu, Ermin Wei
IEEE Conference on Decision and Control (CDC), 2025
Exact Community Recovery in the Geometric Stochastic Block Model
Julia Gaudio, Xiaochun Niu, Ermin Wei
ACM-SIAM Symposium on Discrete Algorithms (SODA), 2024
Nemhauser Prize for Best Student Paper, 2024
Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters
Zhenyu Sun, Xiaochun Niu, Ermin Wei
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
DISH: A Distributed Hybrid Primal-Dual Optimization Framework to Utilize System Heterogeneity
Xiaochun Niu, Ermin Wei
IEEE Conference on Decision and Control (CDC), 2022