Selected Publications & Manuscripts under Review

• Generative Data Science
• Trustworthy Synthetic Data: Fidelity, Utility, Privacy
• Generative Model: Large Language Model, Diffusion Model, GAN
• Machine/Deep Learning Algorithm & Theory
• Trustworthy Machine/Deep Learning: Differential Privacy; Watermarking; Statistical Fariness; Adversarial Robustness
• Statistical Machine/Deep Leanring: Deep Learning Theory; Big Data Theory; Tensor Data Analysis; Bandit
• Statistical Foundations of Data Science
• High-Dimensional Statistics: Minimax Analysis; Time Series/Networked Data; Moderate Dimension
• Mathematical Statistics: Bootstrap; Semi-Nonparametric Inference; Smoothing Spline
• Bussiness-Driven AI
• Business Intelligence: Blockchain; Clinical Trial; Dynamic Pricing; Market Design

Manuscripts patiently awaiting publication :-)

• Dynamic Online Recommendation for Two-Sided Market with Bayesian Incentive Compatibility (with Li, Y. and Dai, X.)
• CTSyn: A Foundational Model for Cross Tabular Data Generation (with Lin, X., Xu, C. and Yang, M.)
• TimeAutoDiff: Combining Autoencoder and Diffusion model for time series tabular data synthesizing (with Suh, N. et al)
• Watermarking Generative Tabular Data (with He, H., Yu, P., Ren, J. and Wu, Y.N.)
• BadGD: A unified data-centric framework to identify gradient descent vulnerabilities (with Wang, C.-H.)
• Latent Energy-Based Odyssey: Black-Box Optimization via Expanded Exploration in the Energy-Based Latent Space (with Yu, P. et al)
• Discriminative Estimation of Total Variation Distance: A Fidelity Auditor for Generative Data (with Tao, L., Xu, S., Wang, C.-H. and Suh, N.)
• Minimax Optimal Fair Classification with Bounded Demographic Disparity (with Zeng, X. and Dobriban, E.)
• Approximation of RKHS Functionals by Neural Networks (with Zhou, T., Suh, N. and Huo, X.)
• Rate-Optimal Rank Aggregation with Private Pairwise Rankings (with Xu, S. and Sun, W.W.)
• Bayes-Optimal Fair Classification with Linear Disparity Constraints via Pre-, In-, and Post-processing (with Zeng, X. and Dorbriban, E.)
• Benefits of Transformer: In-Context Learning in Linear Regression Tasks with Unstructured Data (with Xing, Y., Lin, X., Sub, N. and Song, Q.)
• MissDiff: Training Diffusion Models on Tabular Data with Missing Values (with Ouyang, Y., Xie, L. and Li, C.)
• Utility Theory of Synthetic Data Generation (with Xu, S. and Sun, W.-W.)
• Ranking Differential Privacy (with Xu, S. and Sun, W.W.)
• Differentially Private Bootstrap: New Privacy Analysis and Inference Strategies (with Wang, Z. and Awan, J.)
• Dynamic Matching Bandit For Two-Sided Online Markets (with Li, Y., Wang, C.-H., and Sun, W.)
• Attention Enables Zero Approximation Error (with Fang, Z., Ouyang, Y. and Zhou, D.)
• High-Dimensional Inference over Networks: Linear Convergence and Statistical Guarantees (with Sun, Y., Maros, M. and Scutari, G.)
• On Deep Instrumental Variables Estimate (with Liu, R. and Shang, Z.)

Selected Publications

*: former/current PhD Student; **: former/current Postdoc
• Ouyang*, Xie, Zha and Cheng (2024) Transfer Learning for Diffusion Models , NeurIPS
• Suh** and Cheng (2024) A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models , Annual Review of Statistics and Its Application
• Xia, Wang**, Mabry and Cheng (2024) Advancing Retail Data Science: Comprehensive Evaluation of Synthetic Data, KDD Workshop on GenAI Evaluation
• Ward*, Wang** and Cheng (2024) Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models , KDD Workshop on GenAI Evaluation
• Li*, Cheng and Dai (2024) Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints , ICML
• Ward*, Zeng** and Cheng (2024) FairRR: Pre-Processing for Group Fairness through Randomized Response , AISTATS
• Xing*, Lin*, Song, Xu, Zeng and Cheng (2024) Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective , AISTATS
• Hsieh, Wang** and Cheng (2023) Improve Fidelity and Utility of Synthetic Credit Card Transaction Time Series from Data-centric Perspective, ACM International Conference on AI in Finance -- Workshop
• Wang*, Wang*, Sun and Cheng (2023) Online Regularization towards Always-Valid High-Dimensional Dynamic Pricing , Journal of the American Statistical Association -- T&M
• Xu**, Wang**, Sun and Cheng (2023) Binary Classification under Local Label Differential Privacy Using Randomized Response Mechanisms, Transactions on Machine Learning Research
• Suh**, Lin*, Hsieh, Honarkhah and Cheng (2023) AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing, NeurIPS Workshop on SyntheticData4ML
• Li*, Wang**, Cheng and Song (2023) Optimum-statistical Collaboration Towards General and Efficient Black-box Optimization, Transactions on Machine Learning Research
• Ouyang, Xie and Cheng (2023) Improving Adversarial Robustness by Contrastive Guided Diffusion Process ICML
• Li, Wang** and Cheng (2023) Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms ICLR
• Ning and Cheng (2023) Sparse Confidence Sets for Normal Mean Models Information and Inference: A Journal of the IMA
• Fang** and Cheng (2023) Optimal Learning Rates of Deep Convolutional Neural Networks: Additive Ridge Functions, Transactions on Machine Learning Research
• Zeng**, Dorbriban and Cheng (2022) Fair Bayes-Optimal Classifiers under Predictive Parity NeurIPS
• Cheng, Wang**, Potluru, Balch and Cheng (2022) Downstream Task-Oriented Generative Model Selections on Synthetic Data Training for Fraud Detection Models ACM International Conference on AI in Finance -- Workshop
• Xing*, Song and Cheng (2022) Phase Transition from Clean Training to Adversarial Training NeurIPS
• Xing*, Song and Cheng (2022) Why Do Artificially Generated Data Help Adversarial Robustness? NeurIPS
• Ramprasad*, Li*, Yang, Wang, Sun, and Cheng (2022) Online Bootstrap Inference For Policy Evaluation In Reinforcement Learning JASA -- T&M
• Li*, Wang*, Zhang and and Cheng (2022) Variance Reduction on General Adaptive Stochastic Mirror Descent, Machine Learning Journal (short version accepted in NeurIPS OPT Workshop)
• Song and Cheng (2022) Optimal False Discovery Control of Minimax Estimator Bernoulli
• Yu*, Chao**, and Cheng (2022) Distributed Bootstrap for Simultaneous Inference under High Dimensionality, JMLR
• Wu*, Wang*, Li* and Cheng (2022) Residual Bootstrap Exploration for Stochastic Linear Bandit, UAI
• Xing*, Song and Cheng (2022) Benefit of Interpolation in Nearest Neighbor Algorithms, SIAM Journal on Mathematics of Data Science
• Huang, Huang, Yang** and Cheng (2022) Power Iteration for Tensor PCA, JMLR
• Xing*, Song and Cheng (2022) Unlabelled Data Help: Minimax Analysis and Adversarial Robustness, AISTATS
• Xing*, Song and Cheng (2021) On the Algorithmic Stability of Adversarial Training, NeurIPS
• Liu*, Yang, Shang** and Cheng (2021) Nonparametric Testing under Random Projection, IEEE Transactions on Pattern Analysis and Machine Intelligence Talk Slides
• Li*, Wang* and Cheng (2021) Online Forgetting Process for Linear Regression Models, AISTATS
• Xing*, Song and Cheng (2021) On the Generalization Properties of Adversarial Training, AISTATS
• Hu*, Wang, Lin and Cheng (2021) Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network , AISTATS
• Xing*, Zhang and Cheng (2021) Adversarially Robust Estimate and Risk Analysis in Linear Regression, AISTATS
• Xing*, Song and Cheng (2021) Predictive Power of Nearest Neighbors Algorithm under Random Perturbation, AISTATS
• Chen, Wan, Cai and and Cheng (2020) Machine Learning in/for Blockchain: Future and Challenges, Canadian Journal of Statistics
• Chao**, Wang*, Xing* and and Cheng (2020) Directional Pruning of Deep Neural Networks, NeurIPS [code can be found in Github; theory is based on this work]
• Bai*, Song and and Cheng (2020) Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee, NeurIPS
• Duan*, Qiao and and Cheng (2020) Statistical Guarantees of Distributed Nearest Neighbor Classification Talk Slides, NeurIPS
• Guo and and Cheng (2020) Moderate-Dimensional Inferences on Quadratic Functionals in Ordinary Least Squares , JASA-T&M R Package: MDOLS
• Yu*, Chao** and Cheng (2020) Simultaneous Inference for Massive Data: Distributed Bootstrap, ICML
• Cheng*, Qiao** and Cheng (2020) Mutual Transfer Learning for Massive Data, ICML
• Yang, Shang** and Cheng (2020) Non-asymptotic Theory for Nonparametric Testing, COLT, Talk Slides
• Zheng** and Cheng (2020) Finite Time Analysis of Vector Autoregressive Models under Linear Restrictions, Biometrika, Talk Slides
• Hao*, Zhang and Cheng (2020) Sparse and Low-rank Tensor Estimation via Cubic Sketchings, IEEE-Information Theory, a short version published in AISTATS.
• Wang* and Cheng (2020) Online Batch Decision-Making with High-Dimensional Covariates, AISTATS
• Liu*, Shang** and Cheng (2020) Nonparametric Distributed Learning under General Designs, Electronic Journal of Statistics
• Hao*, Abbasi-Yadkori, Wen and Cheng (2019) Bootstrapping Upper Confidence Bound, NeurIPS
• Shang**, Hao* and Cheng (2019) Nonparametric Bayesian Aggregation for Massive Data, Journal of Machine Learning Research Talk Slides
• Qiao, Duan* and Cheng (2019) Rates of Convergence for Large-scale Nearest Neighbor Classification, NeurIPS
• Liu*, Shang** and Cheng (2019) Sharp Theoretical Analysis for Nonparametric Testing under Random Projection , COLT
• Zhu, Yu* and Cheng (2019) High Dimensional Inference in Partially Linear Models, AISTATS
• Lyu, Sun*, Wang, Liu, Yang and Cheng (2019) Tensor Graphical Model: Non-convex Optimization and Statistical Inference, IEEE-Transactions on Pattern Analysis and Machine Intelligence.
• Liu* and Cheng (2018) Early Stopping for Nonparametric Testing, NIPS Poster
• Xu, Shang** and Cheng (2018) Optimal Tuning for Divide-and-Conquer Kernel Ridge Regression with Massive Data, ICML (oral), 80:5479-5487. An extended version published in Journal of Computational and Graphical Statistics.
• Volgushev, Chao** and Cheng (2018) Distributed Inference for Quantile Regression Processes, Annals of Statistics, To Appear. Talk Slides
• Yu*, Levine and Cheng (2018) Minimax Optimal Estimation in Partially Linear Additive Models under High Dimension, Bernoulli, To Appear.
• Li, Cheng, Fan and Wang (2018) Embracing Blessing of Dimensionality in Factor Models, Journal of the American Statistical Association - Theory & Methods, 113, 380-389
• Hao*, Sun*, Liu and Cheng (2018) Simultaneous Clustering and Estimation of Heterogeneous Graphical Models, Journal of Machine Learning Research, 18(217):1−58.
• Shang** and Cheng (2017) Gaussian Approximation of General Nonparametric Posterior Distributions, Information and Inference, To Appear. In memory of Prof. Jayanta Ghosh
• Shang** and Cheng (2017) Computational Limits of a Distributed Algorithm for Smoothing Spline, Journal of Machine Learning Research, 18(108):1−37. Poster
• Zhang and Cheng (2017) Gaussian Approximation for High Dimensional Vector under Physical Dependence, Bernoulli, To Appear
• Chao**, Vogushev and Cheng (2017) Quantile Processes for Semi and Nonparametric Regression, Electronic Journal of Statistics, 11, 3272 - 3331
• Zhang and Cheng (2017) Simultaneous Inference for High-Dimensional Linear Models, Journal of the American Statistical Association - Theory & Methods, 112, 757-768. R Package: SILM
• Sun*, Lu, Liu and Cheng (2017) Provable Sparse Tensor Decomposition, Journal of the Royal Statistical Society: Series B (Statistical Methodology), 79, 899–916
• Sun*, Qiao and Cheng (2016) Stabilized Nearest Neighbor Classifier and Its Statistical Properties, Journal of the American Statistical Association - Theory & Methods, 111, 1254-1265
• Minsker, Zhao and Cheng (2016) Active Clinical Trials for Personalized Medicine, Journal of the American Statistical Association - Theory & Methods, 111, 875-887
• Zhao, Cheng and Liu (2016) A Partially Linear Framework for Massive Heterogeneous Data. Annals of Statistics, 44, 1400-1437. See Talk Slides, Full Manuscript
  
• Pati, Bhattacharya and Cheng (2015) Optimal Bayesian estimation in random covariate design with a rescaled Gaussian process prior, Journal of Machine Learning Research, 16, 2837−2851
• Sun*, Wang, Liu and Cheng (2015) Non-Convex Statistical Optimization for Sparse Tensor Graphical Model, NIPS (Acceptance Rate: 21.9%).
• Shang** and Cheng (2015) Nonparametric Inference in Generalized Functional Linear Models Annals of Statistics, 43, 1742-1773 (See Talk Slides)
• Cheng and Shang** (2015) Joint Asymptotics for Semi-Nonparametric Regression Models under Partially Linear Structure, Annals of Statistics, 43, 1351-1390 (See Talk Slides)
  
• Cheng, Zhang and Shang** (2015) Sparse and Efficient Estimation for Partial Spline Models with Increasing Dimension, Annals of Institute of Statistical Mathematics, 67, 93-127
  
• Cheng (2015) Moment Consistency of the Exchangeably Weighted Bootstrap for Semiparametric M-Estimation, Scandinavian Journal of Statistics, 42, 665-684
  
• Cheng, Zhou and Huang (2014) Efficient  Semiparametric Estimation in Generalized Partially Linear Additive  Models for Longitudinal/Clustered Data, Bernoulli, 20, 141-163
  
• Shang** and Cheng (2013) Local and Global Asymptotic Inference in Smoothing Spline Models, Annals of Statistics, 41, 2608-2638.
  In the suppl file, [27] is Kosorok, M. R. (2008), and [38] is Pinelis, I. (1994, AoP).
• Cheng (2013). How Many Iterations are Sufficient for Efficient Semiparametric Estimation?, Scandinavian Journal of Statistics, 40, 592-618 (See Talk Slides)
  
• Zhang, Cheng and Liu (2011) Linear or Nonlinear? Automatic Discovery for Partially Linear Models, Journal of the American Statistical Association - Theory & Methods, 106, 1099-1112
  
• Cheng and Wang (2011), Semiparametric Additive Transformation Models under Current Status Data, Electronic Journal of Statistics, 5, 1735-1764
  
• Cheng and Huang (2010) Bootstrap Consistency for General Semiparametric M-estimation Annals of Statistics, 38, 2884-2915 (See Talk Slides)
  
• Cheng (2009), Semiparametric Additive Isotonic Regression Journal of Statistical Planning and Inference, 139, 1980-1991
  
• Cheng and Kosorok (2008), General Frequentist Properties of the Posterior Profile Distribution Annals of Statistics, 36, 1819-1853
  
• Cheng and Kosorok (2008), Higher Order Semiparametric Frequentist Inference with the Profile Sampler Annals of Statistics, 36, 1786-1818
  

Old Manuscripts not Intended for Publication :(

• Bayes-optimal Classifiers under Group Fairness (with Zeng, X. and Dorbriban, E.)
• A Generalization of Regularized Dual Averaging and Its Dynamics (with Chao, S.-K.)
• Enhanced Nearest Neighbor Classification for Crowdsourcing (with Duan, J. and Qiao, X.)
• Residual Bootstrap Exploration for Bandit Algorithms (with Wang, C., Yu, Y. and Hao, B.)
• Sharp Rate of Convergence for Deep Neural Network Classifiers under the Teacher-Student Setting (with Hu, T. and Shang, Z.)
• Enhancing Multi-model Inference with Natural Selection (with Cheng, C.W.)
• Stein Neural Sampler (with Hu et al) Github
• Quadratic Discriminant Analysis under Moderate Dimension (with Yang, Q.)
• Nonparametric Heterogeneity Testing For Massive Data (with Lu, J. and Liu, H.)
• Bootstrapping High Dimensional Time Series (with Zhang, X.) See Talk Slides
• Semiparametric Bernstein-von Mises Theorem: Second Order Studies (with Yang, Y. and Dunson, D.)

Talk Slides

• T1. Bootstrapping High Dimensional Vector: Interplay between Dependence and Dimensionality. Link (presented by my co-author Zhang at SAMSI workshop)
• T2. Nonparametric Inference in Functional Data. Link (presented by my co-author Shang at SAMSI workshop)
• T3. Nearest Neighbor Classifier with Optimal Stability. Link (presented by my PhD student Sun at ISBIS 2014 and SLDM Meeting)
• T4. A Long March towards Joint Asymptotics: My 1^st Steps…. Link
• T5. Semiparametric Model Based Bootstrap. Link
• T6. Bootstrap Consistency for General Semiparametric M-Estimate. Link
• T7.How Many Iterations are Sufficient for Semiparametric Estimation? Link
• T8. Inverse Problems in Semiparametric Statistical Models. Link