|
Lujia Bai
I am a fourth-year Ph.d. student in the Center for Statistical Science, Department of Industrial Engineering at Tsinghua University, advised by Prof. Weichi Wu . In 2020, I obtained my B.Sc. in the School of Statistics and Management, Shanghai University of Finance and Economics.
I am broadly interested in data with complex structure. My current research focuses on non-stationary time series, time-varying network, functional time series and long-range dependence.
I speak Chinese, English and German.
Email
|
|
|
News
2024-04: I have received 2024 IMS Hannan Graduate Student Travel Award.
2024-03: I have received Young Researcher Scholarship for Bernoulli-IMS World Congress.
2024-03: My Contributed Session on Long Memory detection has been accepted by Bernoulli-IMS World Congress. See you in August in Germany!
2024-02: Our paper "Difference-based covariance matrix estimate in time series nonparametric regression with applications to specification tests " has been accepted by Biometrika.
2023-12: I have been admitted to the " Future Professor Programm" from Tsinghua University.
2023-12: I will chair and give a talk in the session "Recent development on statistical analysis of complex dependent data" in CMStatistics 2023 in Berlin.
2023-11: My package 'mlrv' is available on R CRAN .
2023-11: I have won the First Prize of Comprehensive Scholarship of Tsinghua University.
2023-09: Our paper "UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models" is accepted by NeurIPS 2023 .
2023-09: Our paper "Detecting long-range dependence for time-varying linear models" is accepted by Bernoulli .
2023-02: I am visiting Prof. Holger Dette at Ruhr University of Bochum.
|
|
Detecting long-range dependence for time-varying linear models
Lujia Bai*,
Weichi Wu
Bernoulli, accepted
[arXiv]
[Code]
We consider the problem of testing for long-range dependence in time-varying coefficient regression models, where the covariates and errors are locally stationary, allowing complex temporal dynamics and heteroscedasticity. We develop KPSS, R/S, V/S, and K/S-type statistics based on the nonparametric residuals.
|
|
Time-varying correlation network analysis of non-stationary multivariate time series with complex trends
Lujia Bai*,
Weichi Wu
preprint
[arXiv]
This paper proposes a flexible framework for inferring large-scale time-varying and time-lagged correlation networks from multivariate or high-dimensional non-stationary time series with piecewise smooth trends.
|
|
Difference-based covariance matrix estimate in time series nonparametric regression with applications to specification tests
Lujia Bai*,
Weichi Wu
Biometrika, accepted
[arXiv]
[Code]
We propose a novel difference-based and debiased long-run covariance matrix estimator for functional linear models with time-varying regression coefficients, allowing time series non-stationarity, long-range dependence, state-heteroscedasticity and their mixtures. We apply the new estimator to existing tests, overcoming the notorious non-monotonic power phenomena and improving the performance via the residual free formula.
|
|
UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models
Lujia Bai*,
Wenliang Zhao*,
Yongming Rao,
Jie Zhou ,
Jiwen Lu
NeurIPS 2023
[arXiv]
[Code]
[Project Page]
UniPC is a training-free framework designed for the fast sampling of diffusion models, which consists of a corrector (UniC) and a predictor (UniP) that share a unified analytical form and support arbitrary orders.
|
|
Honors and Awards
2023 The First Prize of Comprehensive Scholarship of Tsinghua University
2022 Comprehensive Scholarship of Tsinghua University
2021 Comprehensive Scholarship of Tsinghua University
2019 Top Ten Female College Students in Shanghai, Shanghai University of Finance and Economics
2018 China Merchants Bank Scholarship, Shanghai University of Finance and Economics
2017 National Scholarship, Shanghai University of Finance and Economics
|
|
Conferences and Workshops
Statistical Analysis of Networks, in Coventry, UK, on September 2023.
Discrete Random Structures, in Lausanne, Swizerland, on August 2023.
Data Science and Dependence 2023 Conference, in Heidelberg, Germany, on July 2023.
16th German Probability and Statistics Days, in Essen, Germany, on March 2023.
Invited talk. On CMStatistics 2022.
Best Paper Award. The 2021 International Workshop on Statistical Theory and Related Fields.
Invited talk. On 2021 Xiamen University Symposium on Modern Statistics.
Invited talk. On 2021 ICSA Applied Statistics Symposium in the session structural inference of time series data.
|
|
Teaching Assistants
2020 Fall, Elementary Probability Theory, Tsinghua University.
2021 Spring, Financial Statistics, Tsinghua University.
2021 Fall, Advanced Mathematical Statistics I, Tsinghua University.
2022 Spring, Applied Time Series Analysis, Tsinghua University.
|
|
Academic Services
Journal Reviewer STAT
|
|