Xinghao Qiao

Associate Professor of Statistics

Office: Columbia House, Room 5.15

Mail: Department of Statistics
London School of Economics
Houghton Street
London, WC2A 2AE
United Kingdom

Email: x.qiao@lse.ac.uk

Education

PhD in Business Statistics, Marshall School of Bussiness, University of Southern California, Los Angeles, CA, USA.
M.S. in Statistics, University of Chicago, Chicago, IL, USA.
B.S. in Mathematics and Physics, Academic Talent Program, Tsinghua University, Beijing, China.

Research interests

Functional data analysis: high-dimensional functional data, partially observed functional data, non-Euclidean functional data.
Complex time series analysis: functional time series, high-dimensional time series, factor models, spectral analysis.
High-dimensional statistics: covariance and graphical models, concentration inequalities, simultaneous testing, Gaussian approximation.
Bayesian nonparametrics: conditional variational inference, graph neural network.
High-dimensional econometrics

Some research papers

Inference for High-Dimensional Linear Regression with Correlated Errors (with S. Guo, D. Li and C. Shen). Working paper, 2023.
Convergence of Covariance and Spectral Density Estimates for High-Dimensional Functional Time Series with Applications (with B. Li and W. Wu). Working paper, 2023.
Dynamic Covariance Matrix Estimation via Locally/Globally Adaptive Thresholdings (with S. Guo and Y. Han). Working paper, 2023.
Testing for White Noise in High-Dimensional Functional Time Series (with J. Chang, Q. Jiang and L. Yang). Working paper, 2023.
Empirical Likelihood for Nonparametric Functions with Applications to Regression Discontinuity Designs: Robust Bias-Correction and Wilks Phenomenon (with S. Guo and Y. Hong). Preprint, 2023.
Inference for High-Dimensional Error-in-Variables Vector Autoregression (with C. Chen and Z. Wang). Preprint, 2023.
Factor Models for Matrix-Variate Functional Time Series in High Dimensions (with D. Li and Z. Wang). Preprint, 2023.
Large Covariance Matrix Estimation with Factor-Assisted Variable Clustering (with D. Li and C. Yu). Preprint, 2023.
Large-Scale Multiple Testing of Cross-Covariance Functions with Applications to Functional Network Models (with Q. Fang and Q. Jiang). Preprint, 2023.
Calibrating Weights for Improved Estimation in Factor Models for High-Dimensional Time series (with Z. Wang). Preprint, 2023.
Functional Knockoffs Selection with Applications to Functional Data Analysis in High Dimensions (with Q. Li and M. Long). Preprint, 2023.
From Sparse to Dense Functional Data in High Dimensions: Revisiting Phase Transitions from a Non-Asymptotic Perspective (with S. Guo, D. Li and Y. Wang). Preprint, 2023.
Factor-Guided Estimation of Large Covariance Matrix Function with Conditional Functional Sparsity (with D. Li and Z. Wang). Preprint, 2023.
DF2M: An Explainable Deep Bayesian Nonparametric Model for High-Dimensional Functional Time Series (with Y. Liu, Y. Pei and L. Wang). Preprint, 2023.
On the Modeling and Prediction of High-Dimensional Functional Time Series (with J. Chang, Q. Fang and Q. Yao). Under revision, 2023.
Factor Modelling for High-Dimensional Functional Time Series (with S. Guo and Q. Wang). Under revision, 2023.
EEGNN: Edge Enhanced Graph Neural Network with a Bayesian Nonparametric Graph Model (with Y. Liu, L. Wang, and J. Lam). The 26th International Conference on Artificial Intelligence and Statistics, 2023.
Adaptive Functional Thresholding for Sparse Covariance Function Estimation in High Dimensions. (with S. Guo and Q. Fang). Journal of the American Statistical Association, 2023, in press.
An Autocovariance-based Learning Framework for High-Dimensional Functional Time Series (with J. Chang, C. Chen and Q. Yao). Journal of Econometrics, 2023, in press.
Finite Sample Theory for High-Dimensional Functional/Scalar Time Series with Applications (with Q. Fang and S. Guo). Electronic Journal of Statistics, 2022, 16, 527-591.
CATVI: Conditional and Adaptively Truncated Variational Inference for Bayesian Nonparametrics (with Y. Liu and J. Lam). The 25th International Conference on Artificial Intelligence and Statistics, 2022. Python code to implement the proposed method.
On Consistency and Sparsity for High-Dimensional Functional Time Series with Application to Autoregressions (with S. Guo). Bernoulli, 2023, 29, 451-472. Supplementary material is available here.
Functional Linear Regression: Dependence and Error Contamination (with C. Chen and S. Guo). Journal of Business and Economic Statistics, 2022, 40, 444-457.
Doubly Functional Graphical Models in High Dimensions (with C. Qian, G. James and S. Guo). Biometrika, 2020, 107: 415-431.
Homogeneity Pursuit in Single Index Models based Panel Data Analysis (with H. Lian and W. Zhang). Journal of Business and Economic Statistics, 2021, 39, 386-401.
Functional Graphical Models (with S. Guo and G. James). Journal of the American Statistical Association, 2019, 114, 211-222.
Index Models for Sparsely Sampled Functional Data (with P. Radchenko and G. James). Journal of the American Statistical Association, 2015, 110, 824-836.
Invited discussion of "Clustering Random Curves Under Spatial Dependence" (with G. James and W. Sun). Technometrics, 2012, 54, 123-126.

Teaching

ST311 Artificial Intelligence (Deep Learning and Reinforcement Learning)
ST443 Machine Learning and Data Mining (Statistical Learning)
ST510 Foundations of Machine Learning (PhD level)
ST498 MSc in Data Science Capstone Project
ST300 Regression and Generalised Linear Models

PhD students

Cheng Chen: "Autocovariance-based Statistical Inference for High-Dimensional Function/Scalar Time Series'', Research Offier at SWUFE.
Yirui Liu: "Three Essays in Bayesian Nonparametric Machine Learning'', Quantitative Researcher at J. P. Morgan.
Qin Fang: "High-Dimensional Functional Data/Time Series: Finite-Sample Theory, Adaptive Functional Thresholding and Prediction'', Assistant Professor at the University of Sydney Business School.

Travel plan

With Dong Li (Tsinghua), George Michailidis (UCLA) and Qiwei Yao (LSE), co-organize Tsinghua Sanya International Workshop on "Complex Time Series Analysis: High-Dimensionality, Change-Points, Forecasting and Causality", Sanya, China, 3-7 January, 2024.