My name is Yuchen Xu. I am a Postdoctoral scholar at the Department of Statistics and Data Science, University of California, Los Angeles. Here I work with Professor George Michailidis on topics about panel time series analysis. Prior to that I got my Ph.D from the Department of Statistics & Data Science at Cornell University, advised by Professor David S. Matteson. I am actively engaged in a number of funded grant projects.
My current research interests are high-dimensional time series analysis, image analysis, and panel data analysis, covering topics such as regression, dimension reduction, tensor decomposition, etc. I am also interested in science-integrated applications with topics including material science, finance, medical data analysis, signal processing, and behavior science.
I am currently actively seeking tenure track opportunities in statistics and data science.
Please find my CV here.
I have made our manuscript for the work Joint Learning of Panel VAR Models with Low-Rank and Sparse Structure available as preprint [arXiv].
I will present a poster about transfer learning for Panel VAR model at the 2025 INFORMS Annual Meeting in October [Link].
I will present a poster about transfer learning for Panel VAR model at the 2025 NBER-NSF Time Series Conference in September.
I will present a talk about Panel VAR model with low-rank and sparse structure at an invited JSM session of Advances in High-Dimensional Time Series: Causality, Learning, and Dimension Reduction in August.
09/2023 - Present: Postdoctoral Scholar.
Advisor: Professor George Michailidis, Department of Statistics and Data Science, UCLA.
2019 - 2023: Graduate Research & Teaching Assistant.
Department of Statistics & Data Science, Cornell University.
[Submitted] Xu, Y., Michailidis, G. (2025). Joint Learning of Panel VAR models with Low Rank and Sparse Structure.
[Chapter 1 of PhD Thesis] Xu, Y., Düker, M. C., & Matteson, D. S. (2023). Testing Simultaneous Diagonalizability. Journal of the American Statistical Association, 119 (546), 1513-1525. doi: 10.1080/01621459.2023.2202435.
[Chapter 2 of PhD Thesis] Manzorro, R., Xu, Y., Vincent, J., Rivera, R., Matteson, D., & Crozier, P. (2022). Exploring Blob Detection to Determine Atomic Column Positions and Intensities in Time-Resolved TEM Images with Ultra-Low Signal-to-Noise. Microscopy and Microanalysis, 28 (6), 1917-1930. doi:10.1017/S1431927622000356.
[Chapter 3 of PhD Thesis] Xu, Y., Thomas, A. M., Crozier, P. A., & Matteson, D. S. (2025). Dynamic Atomic Column Detection in Transmission Electron Microscopy Videos via Ridge Estimation. IEEE Transactions on Image Processing, 34, 1588-1601. doi:10.1109/TIP.2025.3543138.
Thomas, A. M., Crozier, P. A., Xu, Y., & Matteson, D. S. (2023). Feature Detection and Hypothesis Testing for Extremely Noisy Nanoparticle Images using Topological Data Analysis. Techonometrics, 65 (4), 590-603. doi: 10.1080/00401706.2023.2203744.
First-Place Winner, Student Paper
Competition Case Studies and Applications track, The Statistical Methods
in Imaging Conference 2023, May 2023.
Title: Dynamic Atomic Column Detection in
Transmission Electron Microscopy Videos via Ridge
Estimation.
Best Student Poster Award, IEEE Western
New York Image and Signal Processing Workshop (WNYISPW), November
2022.
Title: Non-parametric ridge recovery of
TEM image series given temporal parameterization.
The Most Outstanding Students Awards Bronze
Medal, UPSTAT Conference, April 2021.
Title: Recording atomic column positions
and intensities via Blob Detection in noise-degraded TEM
frames.