madxia

XIA, Dong
夏冬

(PhD Georgia Institute of Technology)

Phone: (852) 3469 2244
Email: madxia@ust.hk
Office: Room 3431
Home Page

Associate Professor



Research Interests

Statistical machine learning, high dimensional statistics, optimization and computational algorithms.

Teaching

  • MATH3424  Regression Analysis
  • MATH6912V  Reading Course: Diffusion Model and Flow-based Modelling

Selected Publications

  Article

  1. Computationally efficient and statistically optimal robust high-dimensional linear regression
    • Author(s): Shen, Yinan; Li, Jingyang; Cai, Jianfeng; Xia, Dong
    • Source: Annals of Statistics, v. 53, (1), February 2025, p. 374-399
    • Year: 2025

  2. U-Statistic Reduction: Higher-Order Accurate Risk Control and Statistical-Computational Trade-Off
    • Author(s): Shao, Meijia; Xia, Dong; Zhang, Yuan
    • Source: Journal of the American Statistical Association, January 2025, p. 1-27
    • Year: 2025

  3. Tensors in High-Dimensional Data Analysis: Methodological Opportunities and Theoretical Challenges
    • Author(s): Auddy, Arnab; Xia, Dong; Yuan, Ming
    • Source: Annual Review of Statistics and Its Application, v. 12, November 2024, article number 17, p. 1-25
    • Year: 2024

  4. Optimal Regularized Online Allocation by Adaptive Re-Solving
    • Author(s): Ma, Wanteng; Cao, Ying; Tsang, Hin Kwok; Xia, Dong
    • Source: Operations research, June 2024
    • Year: 2024

  5. Semi-parametric tensor factor analysis by iteratively projected singular value decomposition
    • Author(s): Chen, Eylnn Y; Xia, Dong; Cai, Chencheng; Fan, Jianqing
    • Source: Journal of the Royal Statistical Society Series B: Statistical Methodology, February 2024, article number qkae001
    • Year: 2024

  6. Latent Space Model for Higher-order Networks and Generalized Tensor Decomposition
    • Author(s): Lyu, Zhongyuan; Xia, Dong; Zhang, Yuan
    • Source: Journal of Computational and Graphical Statistics, February 2023
    • Year: 2023

  7. Optimal estimation and computational limit of low-rank Gaussian mixtures
    • Author(s): Lyu, Zhongyuan; Xia, Dong
    • Source: Annals of Statistics, v. 51, (2), April 2023, p. 646-667
    • Year: 2023

  8. INFERENCE FOR LOW-RANK TENSORS—NO NEED TO DEBIAS
    • Author(s): Xia, Dong; Zhang, Anru R.; Zhou, Yuchen
    • Source: Annals of Statistics, v. 50, (2), April 2022, p. 1220-1245
    • Year: 2022

  9. Edgeworth Expansions for Network Moments
    • Author(s): Zhang, Yuan; Xia, Dong
    • Source: Annals of Statistics, v. 50, (2), April 2022, p. 726-753
    • Year: 2022

  10. Provable Tensor-Train Format Tensor Completion by Riemannian Optimization
    • Author(s): Cai, Jianfeng; Li, Jingyang; Xia, Dong
    • Source: Journal of Machine Learning Research, v. 23, April 2022, article number 123, p. 1-77
    • Year: 2022

  11. Normal approximation and confidence region of singular subspaces
    • Author(s): Xia, Dong
    • Source: Electronic Journal of Statistics, v. 15, (2), 2021, p. 3798-3851
    • Year: 2021

  12. Community detection on mixture multi-layer networks via regularised tensor decomposition
    • Author(s): Jing, Bing-Yi; Li, Ting; Lyu, Zhongyuan; Xia, Dong
    • Source: Annals of Statistics, v. 49, (6), December 2021, p. 3181-3205
    • Year: 2021

  13. Statistically Optimal and Computationally Efficient Low Rank Tensor Completion from Noisy Entries
    • Author(s): Xia, Dong; Yuan, Ming; Zhang, Cun-hui
    • Source: Annals of Statistics, v. 49, (1), February 2021, p. 76-99
    • Year: 2021

  14. Statistical Inferences of Linear Forms for Noisy Matrix Completion
    • Author(s): Xia, Dong; Yuan, Ming
    • Source: Journal of the Royal Statistical Society. Series B: Statistical Methodology, v. 83, (1), February 2021, p. 58-77
    • Year: 2021

  15. Effective Tensor Sketching via Sparsification
    • Author(s): Xia, Dong; Yuan, Ming
    • Source: IEEE Transactions on Information Theory, v. 67, (2), February 2021, p. 1356-1369
    • Year: 2021

  16. Confidence Region of Singular Subspaces for Low-rank Matrix Regression
    • Author(s): Xia, Dong
    • Source: IEEE Transactions on Information Theory, v. 65, (11), November 2019, article number 8754764, p. 7437-7459
    • Year: 2019

  17. On Polynomial Time Methods for Exact Low-Rank Tensor Completion
    • Author(s): Xia, Dong; Yuan, Ming
    • Source: Foundations of Computational Mathematics, v. 19, (6), December 2019, p. 1265-1313
    • Year: 2019

  18. Non-asymptotic Bounds for Percentiles of Independent Non-identical Random Variables
    • Author(s): Xia, Dong
    • Source: Statistics and Probability Letters, v. 152, September 2019, p. 111-120
    • Year: 2019

  19. The Sup-norm Perturbation of HOSVD and Low Rank Tensor Denoising
    • Author(s): Xia, Dong; Zhou, Fan
    • Source: Journal of Machine Learning Research, v. 20, 2019, article number 61, p. 1-42
    • Year: 2019

  20. Tensor SVD: Statistical and Computational Limits.
    • Author(s): Zhang, Anru; Xia, Dong
    • Source: IEEE Transactions on Information Theory, v. 64, (11), May 2018, article number 8368145, p. 7311-7338
    • Year: 2018

  21. Variable Selection of Linear Programming Discriminant Estimator
    • Author(s): Xia, Dong
    • Source: Commnication in Statistics - Theory and Methods, v. 46, (7), April 2017, p. 3321-3341
    • Year: 2017

  22. Estimation of Low Rank Density Matrices by Pauli Measurements
    • Author(s): Xia, Dong
    • Source: Electronic Journal of Statistics, v. 11, (1), p. 50-77
    • Year: 2017

  23. Estimation of Low Rank Density Matrices: Bounds in Schatten Norms and Other Distances
    • Author(s): Xia, Dong; Koltchinskii, Vladimir
    • Source: Electronic Journal of Statistics, v. 10, (2), 2016, p. 2717-2745
    • Year: 2016

  24. Optimal Estimation of Low Rank Density Matrices
    • Author(s): Koltchinskii, Vladimir; Xia, Dong
    • Source: Journal of Machine Learning Research, v. 16, September 2015, p. 1757-1792
    • Year: 2015

  Conference paper

  1. High-dimensional Linear Bandits with Knapsacks
    • Author(s): Ma, Wanteng; Xia, Dong; Jiang, Jiashuo
    • Source: Proceedings of Machine Learning Research, v. 235, July 2024, p. 34008 -34037
    • Year: 2024

  2. Perturbation of Linear Forms of Singular Vectors Under Gaussian Noise
    • Author(s): Koltchinskii, Vladimir; Xia, Dong
    • Source: High Dimensional Probability VII: The Cargèse Volume, v. 71, 2016, p. 397-423, Book series: Progress in Probability
    • Year: 2016