Biography

Youngseok Song is an assistant professor of Statistics in the School of Mathematical and Data Sciences at West Virginia University (WVU). His research interests are statistical network analysis, high-dimensional statistics, graphical modeling, large-scale inference, robust statistics and learning, and statistical genomics. Prior to joining WVU, he was a post-doctoral researcher in the Statistical Data Science group at the École Polytechnique Fédérale de Lausanne (EPFL), working with Prof. Sofia C. Olhede. He received his Ph.D. in Statistics from Colorado State University under the supervision of Prof. Wen Zhou.

Interests
  • Statistical network analysis
  • High-dimensional statistics
  • Large-scale inference
  • Graphical modeling
  • Robust statistics
  • Statistical genomics
Education

  • Ph.D. in Statistics, 2021

    Colorado State University

  • M.S. in Statistics, 2017

    Colorado State University

  • M.S. in Mathematics, 2010

    POSTECH

  • B.S. in Mathematics, 2008

    POSTECH

Academic Position

 
 
 
 
 
Assistant Professor
West Virginia University
Aug 2023 – Present Morgantown, WV, USA
 
 
 
 
 
Collaborateur scientifique / Post-doc
EPFL
Sep 2021 – Jul 2023 Lausanne, Switzerland

Publication

Youngseok Song, S.C. Olhede (2026). nethist: An R Package for Nonparametric Graphon Estimation via Network Histograms. Under Review.

Preprint

Youngseok Song, S.C. Olhede (2026). Joint Estimation of Sparse Multilayer Networks via Graph Limits. Under Review.

Preprint

Youngseok Song, M. Darrah (2026). Predicting Missing Connections in a Collaborative Educational Network. Under Review.

E.K. Fischer, Youngseok Song, W. Zhou, K.L. Hoke (2025). Flexibility in Gene Coexpression at Developmental and Evolutionary Timescales. Molecular Biology and Evolution.

Cite DOI

Youngseok Song, Wen Zhou, Wen-Xin Zhou (2023). Large-Scale Inference of Multivariate Regression for Heavy-Tailed and Asymmetric Data. Statistica Sinica.

Cite DOI

See all publications

Software

R packages

  • nethist: Network histogram, a nonparametric graphon estimation (CRAN)

Teaching

West Virginia University

  • STAT 215, Introduction to Probability and Statistics: F23, F24, F26
  • STAT 312, Intermediate Statistical Methods: S26
  • STAT 331/531, Sampling Methods/Sampling Theory and Methods: F25, F26
  • STAT 512, Statistical Methods II: S24, F24, S25

Colorado State University

  • STAT 301, Introduction to Statistical Methods: S20
  • STAT 307, Introduction to Biostatistics: F18, Sm20
  • STAT 472, Statistical Research: Design, Data & Methods: S19, F19, F20, S21
  • STAA 566, Statistical Consulting: Sm21

For a full list, see CV.

Recent Posts

Cartoon by EPFL & UNIL students about misleading data visualization
I would like to introduce a cartoon created by two students from EPFL and one student from UNIL. This is a part of their semester project for the critical data studies class.
Last updated on Aug 19, 2022 1 min read Data visualization, Science communication
Sprase Matrix objects in R
In this post, we take a look sparse matrix objects in R in terms of object size. If most of entries in a matrix are 0, we call the matrix is sparse.
Last updated on Jun 16, 2022 2 min read R
Profiling R code: microbenchmark vs bench
Wickham (2019) is a nice book if you want to learn more about R programming. In Chapter 24, it covers R codes profiling. For profiling codes, the author uses bench package, which I have never used.
Last updated on Nov 1, 2021 3 min read R
Generating multivariate normal samples
Generating multivariate normal sample is important for simulation studies. MASS::mvrnorm() is one of the commonly used functions to generate such random sample (Venables and Ripley 2002). However, it is often ignored that the function is not the fastest way due to error handling parts.
Last updated on Nov 1, 2021 7 min read R

Contact