Synthetic Augmentation in Imbalanced Learning: When It Helps, When It Hurts, and How Much to Add
Preprint, 2026.
Research portfolio
Publications
Selected and complete publications across statistics, machine learning, optimization, and scientific applications.
Selected work
Tensor SVD: Statistical and computational limits
IEEE Transactions on Information Theory, 2018.
Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
The Annals of Statistics, 2018.
Semi-supervised inference: General theory and estimation of means
The Annals of Statistics, 2019.
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
International Conference on Learning Representations (ICLR), 2023 · Notable top 5%.
On geometric connections of embedded and quotient geometries in Riemannian fixed-rank matrix optimization
Mathematics of Operations Research, 2024.
TEMPTED: Time-informed dimensionality reduction for longitudinal microbiome studies
Genome Biology, 2024.
Reliable generation of privacy-preserving synthetic electronic health record time series via diffusion models
Journal of the American Medical Informatics Association, 2024.
Timeline registration for electronic health records
AMIA Summits on Translational Science Proceedings, 2023 · AMIA Data Science Outstanding Paper Award.
Preprints
Work awaiting publication- Zhengchi Ma, Pengfei Lyu, and Anru R. Zhang (2026+). When does synthetic data augmentation improve score-based imbalanced classification?.
- Zhengchi Ma and Anru R. Zhang (2026+). Synthetic augmentation in imbalanced learning: When it helps, When it hurts, and how much to add.
- Jian Lu, Panyu Chen, Miriam Treggiari, Robert Blessing, Danyang Zhuo, Chunhua Weng, William W. Stead, and Anru R. Zhang (2026+). Toward Automated Detection of Documentation Inconsistencies in Electronic Health Records.
- Runshi Tang, Yuefeng Han, and Anru R. Zhang (2026+). Detection is harder than estimation in certain regimes: Inference for moment and cumulant tensors.
- Runshi Tang, Julien Chhor, Olga Klopp, Alexandre B. Tsybakov, and Anru R. Zhang (2026+). Optimal Estimation of Discrete Multiview Distributions under Heteroskedastic Multinomial Sampling.
- Runshi Tang, Anru R. Zhang, Yuefeng Han, and Wei Biao Wu (2026+). Bandable Cumulant Tensors: Optimal Estimation and Applications in Non-Gaussian Data Modeling.
- Fred Zhangzhi Peng, Avishek Joey Bose, Anru R. Zhang, and Alexander Tong (2026+). Coupling Models for One-Step Discrete Generation.
- Fred Zhangzhi Peng, Alexis Fox, Anru R. Zhang, and Alexander Tong (2026+). Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment.
- Pengfei Lyu, Zhengchi Ma, Linjun Zhang, and Anru R. Zhang (2026+). Bias-Corrected Data Synthesis for Imbalanced Learning.
- Yufa Zhou, Yixiao Wang, Surbhi Goel, and Anru R. Zhang (2026+). Why Do Transformers Fail to Forecast Time Series In-Context?, What Can('t) Transformers Do? @ NeurIPS 2025, accepted as an oral presentation (3 out of 68 submissions).
- Chenyin Gao, Han Chen, Anru R. Zhang, and Shu Yang (2026+). Causal inference on sequential treatments via tensor completion.
- Runshi Tang, Julien Chhor, Olga Klopp, and Anru R. Zhang (2026+). Revisit CP tensor decomposition: Statistical optimality and fast convergence.
- Jingyang Li, T. Tony Cai, Dong Xia, and Anru R. Zhang (2026+). Federated PCA and estimation for spiked covariance matrices: Optimal rates and efficient algorithm.
- Brett W. Larsen, Tamara G. Kolda, Anru R. Zhang, and Alex H. Williams (2026+). Tensor decomposition meets RKHS: Efficient algorithms for smooth and misaligned data.
- Shounak Chattopadhyay, Anru R. Zhang, and David Dunson (2026+). Blessing of dimension in Bayesian inference on covariance matrices.
- Arian Maleki, Subhabrata Sen, Sivaraman Balakrishna, Verena Zuber, Chao Gao, Rishabh Dudeja, Christos Thrampoulidis, Anru Zhang, Weijie Su, Jason M. Klusowski, Po-Ling Loh, and Ali Shojaie (2026+). High-dimensional statistics: Reflections on progress and open problems.
Publications
Peer-reviewed and accepted work- Jianbin Tan and Anru R. Zhang (2026+). Smooth flow matching for synthesizing functional data, The Annals of Statistics, to appear.
- Han Chen, Sitan Chen, and Anru R. Zhang (2026+). A provably efficient method for tensor ring decomposition and its applications, SIAM Journal on Mathematics of Data Science, to appear.
- Jianbin Tan, Pixu Shi, and Anru R. Zhang (2026+). Functional-SVD for heterogeneous trajectories: Case studies in health, Journal of the American Statistical Association, to appear.
- Runshi Tang, Runbing Zheng, Anru R. Zhang, and Carey Priebe (2026+). A functional tensor model for dynamic multilayer networks with common invariant subspaces and the RKHS estimation, Journal of Computational and Graphical Statistics, to appear.
- Haotian Zhuang, Xin Gai, Anru R. Zhang, Wenpin Hou, Zhicheng Ji, and Pixu Shi (2026+). Trajectory-guided dimensionality reduction for multi-sample single-cell RNA-seq data reveals biologically relevant sample-level heterogeneity, Bioinformatics, to appear.
- Ayman Ali, Shiyi Jiang, John Rollman, Miriam Treggiari, Zachary Ginsberg, Daniel M. Buckland, Christopher Lindsell, James Jung, Bruce W. Rogers, and Anru R. Zhang (2026). Comparing Clinically Derived Feature Imputation and Phenotype Labels versus Data-Driven Imputation and Clustering Approaches, Proceedings of AMIA Annual Symposium to appear.
- Zihan Zhu, Xin Gai, and Anru R. Zhang (2026+). Functional post-clustering selective inference with applications to EHR, Electronic Journal of Statistics, to appear.
- Fred Zhangzhi Peng, Zachary Bezemek, Jarrid Rector-Brooks, Shuibai Zhang, Michael M. Bronstein, Anru Zhang, Joey Bose, and Alexander Tong (2026). Planner aware path learning in diffusion language models training, International Conference on Learning Representations (ICLR), accepted as an oral presentation (top 1.18% of all submissions).
- Chengzhu Huang and Anru R. Zhang (2026+). High-order accurate inference on manifolds, The Annals of Statistics, to appear.
- Yufa Zhou, Yixiao Wang, Xunjian Yin, Shuyan Zhou, and Anru R. Zhang (2026). The geometry of reasoning: Flowing logics in representation space, International Conference on Learning Representations (ICLR), to appear.
- Xin Gai, Shiyi Jiang, and Anru R. Zhang (2026+). Subtype-aware registration of longitudinal electronic health records, Journal of the American Statistical Association (Applications & Case Studies), to appear.
- Joshua Agterberg and Anru R. Zhang (2026+). Statistical inference for low-rank tensors: heteroskedasticity, subgaussianity, and applications, The Annals of Statistics, to appear.
- Runshi Tang, Tamara G. Kolda, and Anru R. Zhang (2026+). Tensor decomposition with unaligned observations, SIAM Journal on Matrix Analysis and Applications, to appear.
- Raymond Xiong, Panyu Chen, Tianze Dong, Jian Lu, Louis Hu, Nathan Yu, Benjamin Goldstein, Danyang Zhuo, and Anru R. Zhang (2026). Reliable Curation of EHR Dataset via Large Language Models under Environmental Constraints, 2026 IEEE International Conference on Healthcare Informatics.
- Tongyu Li, Fang Yao, and Anru R. Zhang (2026+). Functional tensor regression, Statistica Sinica, to appear.
- Jianbin Tan, Yan Zhang, Chuan Hong, T. Tony Cai, Tianxi Cai, and Anru R. Zhang (2025). Integrated Analysis for Electronic Health Records with Structured and Sporadic Missingness, Journal of Biomedical Informatics, 171, 104933.
- Huifang Ma, Yilong Qu, Xingyuan Zhang, Anru R. Zhang, and Zhicheng Ji (2025). Vispro improves imaging analysis for Visium spatial transcriptomics, Genome Biology, 26, 1-31.
- Pixu Shi, Cameron Martino, Rungang Han, Stefan Janssen, Gregory Buck, Myrna Serrano, Kouros Owzar, Rob Knight, Liat Shenhav, and Anru R. Zhang (2024). TEMPTED: Time-informed dimensionality reduction for longitudinal microbiome studies, Genome Biology, 25, 317.
- Yuetian Luo, Xudong Li, and Anru R. Zhang (2025). Nonconvex factorization and manifold formulations are almost equivalent in low-rank matrix optimization, INFORMS Journal on Optimization, 7, 1-82.
- Joshua Agterberg and Anru R. Zhang (2025). Estimating higher-order mixed memberships via the l_{2,\infty} tensor perturbation bound, Journal of the American Statistical Association, 120, 1214-1224.
- Runshi Tang, Ming Yuan, and Anru R. Zhang (2025). Mode-wise principal subspace pursuit and matrix spiked covariance model, Journal of the Royal Statistical Society, Series B, 87, 232-255.
- Muhang Tian, Bernie Chen, Allan Guo, Shiyi Jiang, and Anru R. Zhang (2024). Reliable generation of privacy-preserving synthetic electronic health record time series via diffusion models, Journal of the American Medical Informatics Association, 31, 2529-2539.
- Jing Lei, Anru R. Zhang, and Zihan Zhu (2024). Computational and statistical thresholds in multi-layer stochastic block models, The Annals of Statistics, 52, 2431–2455.
- Yuetian Luo and Anru R. Zhang (2024). Tensor-on-tensor regression: Riemannian optimization, over-parameterization, statistical-computational gap, and their interplay, The Annals of Statistics, 52, 2583–2612. [R Package]
- Shiyi Jiang, Xin Gai, Miriam Treggiari, William Stead, Yuankang Zhao, David Page, and Anru R. Zhang (2024). Soft phenotyping for sepsis via EHR time-aware soft clustering, Journal of Biomedical Informatics, 152, 104615.
- Yuetian Luo, Xudong Li, and Anru R. Zhang (2024). On geometric connections of embedded and quotient geometries in Riemannian fixed-rank matrix optimization, Mathematics of Operations Research, 49, 782–825.
- Yuetian Luo, Xudong Li, Wen Huang, and Anru R. Zhang (2024). Recursive importance sketching for rank constrained least squares, Operations Research, 72, 237–256.
- Ziang Chen, Jianfeng Lu, and Anru R. Zhang (2024). One-dimensional tensor network recovery, SIAM Journal on Matrix Analysis and Applications, 45, 1217–1244.
- Rungang Han, Pixu Shi, and Anru R. Zhang (2024). Guaranteed functional tensor singular value decomposition, Journal of the American Statistical Association, 119, 995–1007.
- Ilias Diakonikolas, Daniel Kane, Yuetian Luo, and Anru R. Zhang (2023). Statistical and computational limits for tensor-on-tensor association detection, Proceedings of Thirty Sixth Conference on Learning Theory (COLT), 195, 5260–5310.
- Shiyi Jiang, Rungang Han, Krishnendu Chakrabarty, David Page, William Stead, and Anru R. Zhang (2023). Timeline registration for electronic health records, AMIA Summits on Translational Science Proceedings, 291–299.This paper won the Data Science Outstanding Paper Award from the 2023 AMIA Informatics Summit. Only one paper receives this award.
- Yuetian Luo and Anru R. Zhang (2023). Low-rank tensor estimation via Riemannian Gauss-Newton: Statistical optimality and second-order convergence, Journal of Machine Learning Research, 24, 1–48.
- Peter Hoff, Andrew McCormack, and Anru R. Zhang (2023). Core shrinkage covariance estimation for matrix-variate data, Journal of the Royal Statistical Society, Series B, 85, 1659–1679.
- Rungang Han and Anru R. Zhang (2023). Discussion of "Vintage factor analysis with Varimax performs statistical inference", Journal of the Royal Statistical Society, Series B, 85, 1069–1070.
- Sitan Chen, Jerry Li, Yuanzhi Li, and Anru R. Zhang (2023). Learning polynomial transformations, 2023 Annual ACM Symposium on Theory of Computing (STOC).
- Sitan Chen, Sinho Chewi, Jerry Li, Yuanzhi Li, Adil Salim, and Anru R. Zhang (2023). Sampling is as easy as learning the score: Theory for diffusion models with minimal data assumptions, International Conference on Learning Representations (ICLR), accept: notable-top-5%.
- Jiashun Jin, Tracy Ke, Paxton Turner, and Anru R. Zhang (2023). Phase transition for detecting a small community in a large network, 2023 International Conference on Learning Representations (ICLR), accepted.
- Chengzhuo Ni, Yaqi Duan, Munther Dahleh, Mengdi Wang, and Anru R. Zhang (2023). Learning good state and action representations for Markov decision process via tensor decomposition, Journal of Machine Learning Research, 24, 1–53.
A short version was presented at International Symposium on Information Theory (ISIT), 2021. - Rungang Han, Yuetian Luo, Miaoyan Wang, and Anru R. Zhang (2023). Exact clustering in tensor block model: Statistical optimality and computational limit, Journal of the Royal Statistical Society, Series B, 84, 1666–1698. [R Package]This paper received the Student's Paper Award from the Statistical Learning and Data Science Section of the American Statistical Association, 2021.
- Dong Xia, Anru R. Zhang, and Yuchen Zhou (2023). Inference for low-rank tensors -- No need to debias, The Annals of Statistics, 50, 1220–1245.
- Yuetian Luo and Anru R. Zhang (2022). Tensor clustering with planted structures: Statistical optimality and computational limits, The Annals of Statistics, 50, 584–613.
- Tony Cai, Yihong Wu, and Anru R. Zhang (2022). Heteroskedastic PCA: Algorithm, optimality, and applications, The Annals of Statistics, 50, 53–80.
- Rungang Han, Rebecca Willett, and Anru R. Zhang (2022). An optimal statistical and computational framework for generalized tensor estimation, The Annals of Statistics, 50, 1–29.
- Tony Cai, Rungang Han, and Anru R. Zhang (2022). On the non-asymptotic concentration of heteroskedastic Wishart-type matrix, Electronic Journal of Probability, 27, 1–40.
- Yuchen Zhou, Lili Zheng, Yazhen Wang, and Anru R. Zhang (2022). Optimal high-order tensor SVD via tensor-train orthogonal iteration, IEEE Transactions on Information Theory, 66, 5927–5964. [R Package]
- Pixu Shi, Yuchen Zhou, and Anru R. Zhang (2022). High-dimensional log-error-in-variable regression with applications to microbial compositional data analysis, Biometrika, 109, 405–420.
- Ziwei Zhu, Xudong Li, Mengdi Wang, and Anru Zhang (2022). Learning Markov models via low-rank optimization, Operations Research, 70, 2384–2398.
- Tony Cai, Yuchen Zhou, and Anru R. Zhang (2022). Sparse Group Lasso: Optimal Sample Complexity, Convergence Rate, and Statistical Inference, IEEE Transactions on Information Theory, 68, 5975–6002.
- Anru R. Zhang and Kehui Chen (2022). Nonparametric covariance estimation for mixed longitudinal studies, with applications in midlife women's health, Statistica Sinica, 32, 345–365.
- Yuetian Luo, Rungang Han, and Anru R. Zhang (2021). A Schatten-q low-rank matrix perturbation analysis via perturbation projection error bound, Linear Algebra and Its Applications, 630, 225–240.
- Anru R. Zhang, Yuetian Luo, Garvesh Raskutti, and Ming Yuan (2021). A sharp blockwise tensor perturbation bound for orthogonal iteration, Journal of Machine Learning Research, 22, 1–48.This paper received the Biometrics Early-Stage Investigator Award by the Biometrics Section of the American Statistical Association, 2019.
- Anru R. Zhang, Yuetian Luo, Garvesh Raskutti, and Ming Yuan (2020). ISLET: fast and optimal low-rank tensor regression via importance sketchings, SIAM Journal on Mathematics of Data Science, 2, 444–479. [R package]
- Yuetian Luo and Anru R. Zhang (2020). Open problem: Average-case hardness of hypergraphic planted clique detection, Conference on Learning Theory (COLT), 125, 3852–3856. [talk and slides]
- Anru R. Zhang and Yuchen Zhou (2020). On the non-asymptotic and sharp tail bounds of random variables, Stat, 9, e314.
- Botao Hao, Anru R. Zhang, and Guang Cheng (2020). Sparse and low-rank tensor estimation via cubic sketchings, IEEE Transactions on Information Theory, 66, 9.
A short version published in Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2020. - Yuanpei Cao, Anru R. Zhang, and Hongzhe Li (2020). Multi-sample estimation of bacterial composition matrix in metagenomics data, Biometrika, 107, 75–92.
- Anru R. Zhang and Mengdi Wang (2020). Spectral state compression of Markov processes, IEEE Transactions on Information Theory, 66, 3202–3231.
- Anru Zhang (2019). Cross: Efficient low-rank tensor completion, The Annals of Statistics, 47, 936–964. [R package]
- Anru Zhang and Rungang Han (2019). Optimal sparse singular value decomposition for high-dimensional high-order data, Journal of the American Statistical Association, 114, 1708–1725. [R package]
- Anru Zhang, Lawrence Brown, and Tony Cai (2019). Semi-supervised inference: General theory and estimation of means, The Annals of Statistics, 47, 2538–2566.
- Anru Zhang and Dong Xia (2018). Tensor SVD: Statistical and computational limits, IEEE Transactions on Information Theory, 64, 1–28. [An R implementation]
- Quan Zhou, Philip Ernst, Kari Lock Morgan, Donald Rubin, and Anru Zhang (2018). Sequential rerandomization, Biometrika, 105, 745–752.
- Tony Cai and Anru Zhang (2018). Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics, The Annals of Statistics, 46, 60–89.
- Mengdi Wang, Xudong Li, and Anru Zhang (2018). Estimation of Markov chain via rank-constrained likelihood, International Conference on Machine Learning (ICML), PMLR 80:3033–3042.
- Tianxi Cai, Tony Cai, and Anru Zhang (2016). Structured matrix completion with applications in genomic data integration, Journal of the American Statistical Association, 111, 621–633. [R package]
- Pixu Shi, Anru Zhang, and Hongzhe Li (2016). Regression analysis for microbiome compositional data, The Annals of Applied Statistics, 10, 1019–1040. [Matlab package]
- Hyunseung Kang, Anru Zhang, Tony Cai, and Dylan Small (2016). Instrumental variables estimation with some invalid instruments and its application to Mendelian randomization, Journal of the American Statistical Association, 111, 132–144. [R Package]
- Tony Cai and Anru Zhang (2016). Minimax rate-optimal estimation of high-dimensional covariance matrices with incomplete data, Journal of Multivariate Analysis, 150, 55–74.
- Tony Cai and Anru Zhang (2016). Inference for high-dimensional differential correlation matrices, Journal of Multivariate Analysis, 143, 107–126.
- Tony Cai and Anru Zhang (2015). ROP: matrix recovery via rank-one projections, The Annals of Statistics, 43, 102–138.
- Tony Cai and Anru Zhang (2014). Sparse representation of a polytope and recovery of sparse signals and low-rank matrices, IEEE Transactions on Information Theory, 60, 122–132.
- Tony Cai and Anru Zhang (2013). Compressed sensing and affine rank minimization under restricted isometry, IEEE Transactions on Signal Processing, 61, 3279–3290.
- Tony Cai and Anru Zhang (2013). Sharp RIP bound for sparse signal and low-rank matrix recovery, Applied and Computational Harmonic Analysis, 35, 74–93.
Collaborative research
Interdisciplinary collaborations- Chenyin Gao, Shu Yang, and Anru R. Zhang (2026). Self-supervised imaging denoising via low-rank tensor approximated convolutional neural network, IET Image Processing, 20, 13205.
- Sreekanth Vemulapalli, Fawaz Alenezi, Hyeon Jeong, Anna Giczewska, Karen Chiswell, Pamela Douglas, Anru R. Zhang, Svati Shah, Ricardo Henao, and Andrew Wang (2025). Machine learning computer vision point of care decision support of echocardiographic identification of hypertrophic cardiomyopathy, JACC: Advances, 4, 101746.
- Annalise Schweickart, Richa Batra, Bryan J. Neth, Cameron Martino, Liat Shenhav, Anru R. Zhang, et al. (2024). Serum and CSF metabolomics analysis shows Mediterranean Ketogenic Diet mitigates risk factors of Alzheimer's disease, npj Metabolic Health and Disease, 2, 15.
- Zachary M. Burcham, Aeriel D. Belk, Bridget B. McGivern, Amina Bouslimani, Parsa Ghadermazi, Cameron Martino, Liat Shenhav, Anru R. Zhang, et al. (2024). Universal interkingdom microbial network decomposes mammals despite varied climate, location, and seasonal influence, Nature Microbiology, 9, 595–613.
- Anru R. Zhang, Ryan Bell, Chen An, Runshi Tang, Shana Hall, Cliburn Chan, Kareem Al-Khalil, and Christina Meade (2023). Cocaine use prediction with tensor-based machine learning on multimodal MRI connectome data, Neural Computation, 36, 107–127.
- Aditi U. Gurkar, Akos A. Gerencser, Ana L. Mora, Andrew C. Nelson, Anru R. Zhang, et al. Spatial mapping of cellular senescence: emerging challenges and opportunities, Nature Aging, 3, 776–790, 2023.
- Sheri Towe, Runshi Tang, Matt Gibson, Anru R. Zhang, and Christina Meade. Longitudinal changes in neurocognitive performance related to drug use intensity in a sample of persons with and without HIV who use stimulants, Drug and Alcohol Dependence, to appear.
- Christine Park, Beiyu Liu, Stephen C. Harward, Anru R. Zhang, et al. Ventriculomegaly and postoperative intraventricular blood predict cerebrospinal fluid diversion following posterior fossa tumor resection, Journal of Neurosurgery: Pediatrics, 28, 533–543, 2021.
- Chenyu Zhang, Rungang Han, Anru Zhang, and Paul Voyles. Denoising Atomic Resolution 4D Scanning Transmission Electron Microscopy Data with Tensor Singular Value Decomposition, Ultramicroscopy, 219, 113123, 2020.
- Wan, C. et al. LTMG: a novel statistical modeling of transcriptional expression states in single-cell RNA-Seq data, Nucleic Acids Research, 2019.
Other manuscripts
Thesis and early work- High-dimensional statistical inference: from vector to matrix
PhD Thesis, 2015.