Preprints:
[P4] On the expressive power of subgraph graph neural networks for graphs with bounded cycles
Ziang Chen, Qiao Zhang, and Runzhong Wang
[ArXiv]
[P3] Residual connections provably mitigate oversmoothing in graph neural networks
Ziang Chen, Zhengjiang Lin, Shi Chen, Yury Polyanskiy, and Philippe Rigollet
[ArXiv]
[P2] Expressive power of graph neural networks for (mixed-integer) quadratic programs
Ziang Chen, Xiaohan Chen, Jialin Liu, Xinshang Wang, and Wotao Yin
[ArXiv]
[P1] Exact and efficient representation of totally anti-symmetric functions
Ziang Chen and Jianfeng Lu
[ArXiv]
Refereed Journal Papers:
[J8] Fully discretized Sobolev gradient flow for the Gross-Pitaevskii eigenvalue problem
Ziang Chen, Jianfeng Lu, Yulong Lu, and Xiangxiong Zhang
Mathematics of Computation, to appear [ArVix]
[J7] One-dimensional tensor network recovery
Ziang Chen, Jianfeng Lu, and Anru R. Zhang
SIAM Journal on Matrix Analysis and Applications, 45(3), 1217 – 1244 (2024) [Journal] [ArXiv]
[J6] On the convergence of Sobolev gradient flow for the Gross-Pitaevskii eigenvalue problem
Ziang Chen, Jianfeng Lu, Yulong Lu, and Xiangxiong Zhang
SIAM Journal on Numerical Analysis, 62(2), 667-691 (2024) [Journal] [ArXiv]
[J5] Representation theorem for multivariable totally symmetric functions
Chongyao Chen, Ziang Chen, and Jianfeng Lu
Communications in Mathematical Sciences, 22(5), 1195-1201 (2024) [Journal] [ArXiv]
[J4] On the global convergence of randomized coordinate gradient descent for nonconvex optimization
Ziang Chen, Yingzhou Li, and Jianfeng Lu
SIAM Journal on Optimization, 33(2), 713-738 (2023) [Journal] [ArXiv]
[J3] A regularity theory for static Schr\”odinger equations on $\mathbb{R}^d$ in spectral Barron spaces
Ziang Chen, Jianfeng Lu, Yulong Lu, and Shengxuan Zhou
SIAM Journal on Mathematical Analysis, 55(1), 557-570 (2023) [Journal] [ArXiv]
[J2] A trust-region method for nonsmooth nonconvex optimization
Ziang Chen, Andre Milzarek, and Zaiwen Wen
Journal of Computational Mathematics, 41(4), 683-716 (2023) [Journal] [ArXiv]
[J1] Tensor ring decomposition: optimization landscape and one-loop convergence of alternating least squares
Ziang Chen, Yingzhou Li, and Jianfeng Lu
SIAM Journal on Matrix Analysis and Applications, 41(3), 1416-1442 (2020) [Journal] [ArXiv]
Refereed Conference Papers:
[C10] On designing general and expressive quantum graph neural networks with applications to MILP instance representation
Xinyu Ye, Hao Xiong, Jianhao Huang, Ziang Chen, Jia Wang, and Junchi Yan
International Conference on Learning Representations (ICLR) 2025 [Proceedings]
[C9] Rethinking the capacity of graph neural networks for branching strategy
Ziang Chen, Jialin Liu, Xiaohan Chen, Xinshang Wang, and Wotao Yin
Advances in Neural Information Processing Systems (NeurIPS) 2024 [Proceedings] [ArXiv]
[C8] Mean-field analysis for learning subspace-sparse polynomials with Gaussian input
Ziang Chen and Rong Ge
Advances in Neural Information Processing Systems (NeurIPS) 2024 [Proceedings] [ArXiv]
[C7] Certified machine unlearning via noisy stochastic gradient descent
Eli Chien, Haoyu Wang, Ziang Chen, and Pan Li
Advances in Neural Information Processing Systems (NeurIPS) 2024 [Proceedings] [ArXiv]
[C6] Langevin unlearning: a new perspective of noisy gradient descent for machine unlearning
Eli Chien, Haoyu Wang, Ziang Chen, and Pan Li
Advances in Neural Information Processing Systems (NeurIPS) 2024 (spotlight) [Proceedings] [ArXiv]
[C5] Efficient algorithms for sum-of-minimum optimization
Lisang Ding, Ziang Chen, Xinshang Wang, and Wotao Yin
International Conference on Machine Learning (ICML) 2024 [Proceedings] [ArXiv]
[C4] On representing mixed-integer linear programs by graph neural networks
Ziang Chen, Jialin Liu, Xinshang Wang, Jianfeng Lu, and Wotao Yin
International Conference on Learning Representations (ICLR) 2023 [Proceedings] [ArXiv]
[C3] On representing linear programs by graph neural networks
Ziang Chen, Jialin Liu, Xinshang Wang, Jianfeng Lu, and Wotao Yin
International Conference on Learning Representations (ICLR) 2023 (spotlight) [Proceedings] [ArXiv]
[C2] HeteRSGD: tackling heterogeneous sampling costs via optimal reweighted stochastic gradient descent
Ziang Chen, Jianfeng Lu, Huajie Qian, Xinshang Wang, and Wotao Yin
International Conference on Artificial Intelligence and Statistics (AISTATS) 2023 [Proceedings]
[C1] On the representation of solutions to elliptic PDEs in Barron spaces
Ziang Chen, Jianfeng Lu, and Yulong Lu
Advances in Neural Information Processing Systems (NeurIPS) 2021 (spotlight) [Proceedings] [ArXiv]
Others:
[O1] Mathematical analysis of high-dimensional algorithms and models
Ziang Chen
Ph.D. Dissertation, Duke University, 2023 [DukeSpace] [ProQuest]