Preprints
Inference on Gaussian mixture models with dependent labels,
Seunghyun Lee, Rajarshi Mukherjee and Sumit Mukherjee,
preprint, 2025. [arXiv]
CLT in high-dimensional Bayesian linear regression with low SNR,
Seunghyun Lee, Nabarun Deb and Sumit Mukherjee,
preprint, 2025. [arXiv]
Identifiability of latent causal graphical models without pure children,
Seunghyun Lee and Yuqi Gu,
preprint, 2025. [arXiv]
Manuscripts under revision
Fluctuations in random field Ising models,
Seunghyun Lee, Nabarun Deb and Sumit Mukherjee,
"Major Revision" at Annals of Applied Probability, 2025. [arXiv]
Deep Discrete Encoders: identifiable deep generative models for rich data with discrete latent layers,
Seunghyun Lee and Yuqi Gu,
"Major Revision" at the Journal of American Statistical Association, 2025. [arXiv], [code]
Accepted manuscripts
Exploratory general-response cognitive diagnostic models with higher-order structures,
Jia Liu, Seunghyun Lee and Yuqi Gu,
Psychometrika, 2025. [Journal]
New paradigm of identifiability in cognitive diagnostic models: beyond categorical responses,
Seunghyun Lee and Yuqi Gu,
Psychometrika, 89(4): 1304-1336, 2024. [Journal], [code]
Latent conjunctive Bayesian network: unify attribute hierarchy and Bayesian network for cognitive diagnosis,
Seunghyun Lee and Yuqi Gu,
Annals of Applied Statistics, 18(3): 1988-2011, 2024. [Journal], [arXiv], [code]
Conditions for bubbles to arise under heterogeneous beliefs,
Seunghyun Lee and Hyungbin Park,
Quantitative Finance (Feature article), 22(3): 409-421, 2022. [Journal], [arXiv]
A modified Cahn-Hilliard equation for 3D volume reconstruction from two planar cross sections,
Seunggyu Lee et. al,
J. KSIAM, 19(1): 47-56, 2015. [Journal]
CLT in Bayesian linear regression - INFORMS Applied Probability Society (APS) Conference, Georgia Tech, GA [slides]
Gaussian mixture models with dependent labels - Northeast Probability Seminar (NEPS), Columbia University, NY (Nov 2024) [slides]
Latent conjunctive Bayesian network - International Meeting of the Psychometric Society (IMPS), Prague, Czech Republic (July 2024) [poster]
New paradigm of general-response cognitive diagnostic models - International Meeting of the Psychometric Society (IMPS), University of Maryland, MD (July 2023) [slides]