Research Interests
Efficient machine learning and AI,
(Hyper)graph network analysis,
Generative modeling and representation learning for unstructured data,
Uncertainty quantification, high-dimensional statistics
Journal Publications
Supervised homogeneity fusion: a combinatorial approach.
W. Wang*, S. Wu*, Z. Zhu, L. Zhou, P.X.K. Song. The Annals of Statistics, 52(1): 285-310, 2024.
On sure early selection of the best subset.
Z. Zhu*, S. Wu*. [arXiv] [GitHub] IEEE Transactions on Information Theory, 70(12): 8870-8891, 2024.
A distributed community detection algorithm for large scale networks under stochastic block models.
S. Wu*, Z. Li*, X. Zhu. Computational Statistics and Data Analysis, vol. 187, 2023.
Conference Proceedings
ReLaSH: Reconstructing joint latent spaces for efficient generation of synthetic hypergraphs with hyperlink attributes. F. Ma*, S. Wu*, G. Xu, J. Zhu. The Fourteenth International Conference on Learning Representations, 2026.
Selected Preprints
Denoising diffused embeddings: a generative approach for hypergraphs.
S. Wu, J. Yang, G. Xu, J. Zhu. [arXiv] Under major revision at Journal of the American Statistical Association.
A general latent embedding approach for modeling non-uniform high-dimensional sparse hypergraphs with multiplicity.
S. Wu, G. Xu, J. Zhu. [arXiv] [GitHub] Under major revision at Journal of the American Statistical Association.
Statistical inference on latent space models for network data.
J. Li*, S. Wu*, C. Cui, G. Xu, J. Zhu. [arXiv] Under major revision at the Annals of Statistics.
Latent space directed counting network models with node covariates for citation exchange between statistical journals.
S. Wu, T. Zhang, G. Xu, J. Zhu. Submitted.
Efficient synthetic network generation via latent embedding reconstruction.
F. Jiang, Y. Bu, S. Wu, G. Xu, J. Zhu. Submitted.
*: (co-) first author / equal contribution