Gunwoong Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Gunwoong Park has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Donguk Shin
Department of Statistics, Seoul National University, Seoul, Republic of Korea
2 shared publications - Junhyoung Chung
Department of Statistics, Seoul National University, Seoul, Republic of Korea
2 shared publications - Youngmin Ahn
Department of Statistics, Seoul National University, Seoul, Republic of Korea
2 shared publications Jaemin Lee
Department of Statistics University of Seoul Seoul 02504 Korea
1 shared publication- Kyoungjae Lee
Department of Statistics, Sungkyunkwan university
1 shared publication - Semin Choi
School of Cross-Disciplinary Studies, University of Seoul, Seoul, Republic of Korea
1 shared publication
Latest Publications
- 29 June 2026
- Published by Springer Nature in Journal of the Korean Statistical Society
- p. 1-28
Comparison of identifiability conditions in linear additive noise models
- 29 June 2026
- Published by Springer Nature in Journal of the Korean Statistical Society
- p. 1-28
Comparison of identifiability conditions in linear additive noise models
- Open Access
- 21 January 2025
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 54 (2) , 643-644
Correction: Learning distribution-free anchored linear structural equation models in the presence of measurement error
- 21 January 2025
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 54 (2) , 643-644
Open AccessCorrection: Learning distribution-free anchored linear structural equation models in the presence of measurement error
- Open Access
- 31 December 2024
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 54 (2) , 361-385
Learning distribution-free anchored linear structural equation models in the presence of measurement error
This study tackles the challenge of identifiability in distribution-free anchored linear structural equation models (SEMs), where the observed variables are imperfect measures for the target variables, and the error distributions are not restricted to being Gaussian. It introduces the geometry-faithfulness assumption, ensuring that partial correlations serve as direct indicators of d-separation/connection. The study establishes the identifiability of distribution-free anchored linear SEMs under the same identifiability conditions for anchored Gaussian linear SEMs, but by replacing the faithfulness assumption with the geometry-faithfulness assumption. Moreover, it shows that the learning algorithm leveraging the PC algorithm with Fisher’s z-test, originally designed for anchored Gaussian linear SEMs, remains applicable and effective for distribution-free anchored linear SEMs. It also provides statistical guarantees for the proposed algorithm, including the strong geometry-faithfulness assumption, ensuring its consistency. These theoretical contributions are validated through extensive numerical experiments and the analysis of real galaxy data.
- 31 December 2024
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 54 (2) , 361-385
Open AccessLearning distribution-free anchored linear structural equation models in the presence of measurement error
This study tackles the challenge of identifiability in distribution-free anchored linear structural equation models (SEMs), where the observed variables are imperfect measures for the target variables, and the error distributions are not restricted to being Gaussian. It introduces the geometry-faithfulness assumption, ensuring that partial correlations serve as direct indicators of d-separation/connection. The study establishes the identifiability of distribution-free anchored linear SEMs under the same identifiability conditions for anchored Gaussian linear SEMs, but by replacing the faithfulness assumption with the geometry-faithfulness assumption. Moreover, it shows that the learning algorithm leveraging the PC algorithm with Fisher’s z-test, originally designed for anchored Gaussian linear SEMs, remains applicable and effective for distribution-free anchored linear SEMs. It also provides statistical guarantees for the proposed algorithm, including the strong geometry-faithfulness assumption, ensuring its consistency. These theoretical contributions are validated through extensive numerical experiments and the analysis of real galaxy data.
- Open Access
Bayesian Approach to Linear Bayesian Networks
This study proposes the first Bayesian approach for learning high-dimensional linear Bayesian networks. The proposed approach iteratively estimates each element of the topological ordering from backward and its parent using the inverse of a partial covariance matrix. The proposed method successfully recovers the underlying structure when Bayesian regularization for the inverse covariance matrix with unequal shrinkage is applied. Specifically, it shows that the number of samples $n = Ω( d_M^2 \log p)$ and $n = Ω(d_M^2 p^{2/m})$ are sufficient for the proposed algorithm to learn linear Bayesian networks with sub-Gaussian and 4m-th bounded-moment error distributions, respectively, where $p$ is the number of nodes and $d_M$ is the maximum degree of the moralized graph. The theoretical findings are supported by extensive simulation studies including real data analysis. Furthermore the proposed method is demonstrated to outperform state-of-the-art frequentist approaches, such as the BHLSM, LISTEN, and TD algorithms in synthetic data.Open AccessBayesian Approach to Linear Bayesian Networks
This study proposes the first Bayesian approach for learning high-dimensional linear Bayesian networks. The proposed approach iteratively estimates each element of the topological ordering from backward and its parent using the inverse of a partial covariance matrix. The proposed method successfully recovers the underlying structure when Bayesian regularization for the inverse covariance matrix with unequal shrinkage is applied. Specifically, it shows that the number of samples $n = Ω( d_M^2 \log p)$ and $n = Ω(d_M^2 p^{2/m})$ are sufficient for the proposed algorithm to learn linear Bayesian networks with sub-Gaussian and 4m-th bounded-moment error distributions, respectively, where $p$ is the number of nodes and $d_M$ is the maximum degree of the moralized graph. The theoretical findings are supported by extensive simulation studies including real data analysis. Furthermore the proposed method is demonstrated to outperform state-of-the-art frequentist approaches, such as the BHLSM, LISTEN, and TD algorithms in synthetic data. - 14 November 2023
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 53 (1) , 132-148
Asymptotic bias of the $\ell _2$-regularized error variance estimator- 14 November 2023
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 53 (1) , 132-148
Asymptotic bias of the $\ell _2$-regularized error variance estimator- 19 January 2022
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 51 (3) , 758-779
Robust estimation of Gaussian linear structural equation models with equal error variances
- 19 January 2022
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 51 (3) , 758-779
Robust estimation of Gaussian linear structural equation models with equal error variances
Comparison of attributed network clustering approaches to analysing Seoul public bike stations
Network clustering is a fundamental task that discovers innate communities or groups in networks. Hence, network clustering methods such as spectral clustering and regularized spectral clustering have been applied in a wide range of realms. On top of a network structure, it is known in social network analysis that incorporates information from each vertex can be beneficial. This has led to the development of a series of attributed network clustering algorithms that utilize not only network connectivity but also vertex covariates in order to uncover latent clusters. This paper compares the performance of state‐of‐the‐art attributed network clustering approaches focused on detecting clusters of Seoul public bike stations. The data set consists of trip information over the bike station network in 2019. Spatial information about the bike stations is posed as vertex attributes. We show that certain attributed network clustering methods are well suited to detecting explainable clusters of bike rental stations. The results can help bike‐sharing operators better understand system usage and learn how to improve service quality in the existing system.
Comparison of attributed network clustering approaches to analysing Seoul public bike stations
Network clustering is a fundamental task that discovers innate communities or groups in networks. Hence, network clustering methods such as spectral clustering and regularized spectral clustering have been applied in a wide range of realms. On top of a network structure, it is known in social network analysis that incorporates information from each vertex can be beneficial. This has led to the development of a series of attributed network clustering algorithms that utilize not only network connectivity but also vertex covariates in order to uncover latent clusters. This paper compares the performance of state‐of‐the‐art attributed network clustering approaches focused on detecting clusters of Seoul public bike stations. The data set consists of trip information over the bike station network in 2019. Spatial information about the bike stations is posed as vertex attributes. We show that certain attributed network clustering methods are well suited to detecting explainable clusters of bike rental stations. The results can help bike‐sharing operators better understand system usage and learn how to improve service quality in the existing system.
- 1 January 2020
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 49 (1) , 276-292
Identifiability of Gaussian linear structural equation models with homogeneous and heterogeneous error variances
- 1 January 2020
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 49 (1) , 276-292
Identifiability of Gaussian linear structural equation models with homogeneous and heterogeneous error variances