I am a third-year Ph.D. student in the Department of Statistics & Data Science at Carnegie Mellon University. I hold a B.S. in Mathematical Sciences from Seoul National University.

I study theoretical aspects of machine learning, ranging from optimization theory to statistics. My recent interest spans optimal transport and continuous dynamics with real-world applications, including physical sciences.

Prior to CMU, I worked as a research scientist at Krafton AI and as a quantitative analyst in Hyperithm. At SNU, I was fortunate to be advised by Professors Ernest K. Ryu and Sanghack Lee on research projects around theoretical aspects of machine learning, mainly optimization theory and graphical models.

You can find my CV here.

Contact

Email: soheuny [at] andrew [dot] cmu [dot] edu

News

• 2025.08. A paper entitled “Convergence Analyses of Davis–Yin Splitting via Scaled Relative Graphs II: Convex Optimization Problems” has been accepted to Optimization.
• 2024.12. I will be presenting our work entitled “Toward Model-Agnostic Detection of New Physics Using Data-Driven Signal Regions” at ML4PS Workshop at NeurIPS 2024.
• 2024.06. A paper entitled “Convergence Analyses of Davis-Yin Splitting via Scaled Relative Graphs” has been accepted to SIAM Journal on Optimization (SIOPT).
• 2024.01. A paper entitled “Filter, Rank, and Prune: Learning Linear Cyclic Gaussian Graphical Models” has been accepted in AISTATS 2024.