Insung Kong

About me

I am a postdoctoral researcher at University of Twente, working with Johannes Schmidt-Hieber. Before that, I completed my Ph.D. studies at the Seoul National University under the supervision of Yongdai Kim in 2024. 

My research focuses on statistical machine learning, deep learning theory, trustworthy AI, and Bayesian statistics.

Currently, I’m working on a project funded by the European Research Council that extends mathematics and statistics from artificial neural networks to biological neural networks.

Employment

• 2024  -                University of Twente, Enschede, Netherlands

        Postdoctoral researcher

Education

• 2018 - 2024     Seoul Natioanal University, Seoul, Republic of Korea

    Doctor of Philsosphy, Statistics

    Thesis: Posterior Concentration Rates of Bayesian Neural Networks [pdf]

• 2013-2018      Seoul Natioanal University, Seoul, Republic of Korea

    Bachelor of Science, Statistics

• 2010-2013      Gyeonggi Science High School, Suwon, Republic of Korea

Submitted Papers

• Bayesian Additive Regression Trees for functional ANOVA model [pdf]

        Seokhun Park, Insung Kong, Yongdai Kim.

• On the use of supervised anomaly detection algorithms for extremely imbalanced data

        Kyungseon Lee, Jongjin Lee, Insung Kong, Yongdai Kim.

• On the expressivity of deep Heaviside networks [pdf]

        Insung Kong, Juntong Chen, Sophie Langer, Johannes Schmidt-Hieber.

• ReLU integral probability metric and its applications [pdf]

        Yuha Park, Kunwoong Kim, Insung Kong, Yongdai Kim. 

• Uncertainty Quantification of Group-fair Models via Gibbs Posterior

        Jihu Lee, Kunwoong Kim, Insung Kong, Yongdai Kim.

Publications

• Tensor Product Neural Networks for Functional ANOVA Model [pdf]

        Seokhun Park, Insung Kong, Yongchan Choi, Chanmoo Park, Yongdai Kim. International Conference on Machine Learning (ICML). 2025.

• Learning deep generative models based on binomial log-likelihood [pdf]

        Hwichang Jeong, Insung Kong, Yongdai Kim. Neurocomputing. 2025.

• Posterior concentrations of fully-connected Bayesian neural networks with general priors on the weights [pdf]

        Insung Kong, Yongdai Kim. Journal of Machine Learning Research (JMLR). 2025.

• Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics [pdf] [arxiv]

        Insung Kong*, Kunwoong Kim*, Yongdai Kim. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2025.

• Fairness Through Matching [pdf]

        Kunwoong Kim, Insung Kong, Jongjin Lee, Minwoo Chae, Sangchul Park, Yongdai Kim. Transaction on Machine Learning Research (TMLR). 2024.

• On Measuring the Quality of Group Fairness [pdf]

        Kunwoong Kim, Insung Kong, Jongjin Lee, Minwoo Chae, Sangchul Park, Yongdai Kim. Journal of Artificial Intelligence Research and Applications. 2024.

• Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation [pdf]

        Dongyoon Yang, Insung Kong, Yongdai Kim. International Conference on Computer Vision (ICCV). 2023.

• Covariate balancing using the integral probability metric for causal inference [pdf]

        Insung Kong, Yuha Park, Joonhyuk Jung, Kwonsang Lee, Yongdai Kim. International Conference on Machine Learning (ICML). 2023.

• Masked Bayesian Neural Networks: Theoretical Guarantee and its Posterior Inference [pdf]

        Insung Kong, Dongyoon Yang, Jongjin Lee, Ilsang Ohn, Gyuseung Baek, Yongdai Kim. International Conference on Machine Learning (ICML). 2023.

• Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples [pdf]

        Dongyoon Yang, Insung Kong, Yongdai Kim. International Conference on Machine Learning (ICML). 2023.

• Learning fair representation with a parametric integral probability metric [pdf]

        Dongha Kim, Kunwoong Kim, Insung Kong, Ilsang Ohn, Yongdai Kim. International Conference on Machine Learning (ICML). 2022.

Teaching

• Spring 2024     Instructor, Statistical Machine Learning

    Sookmyung Women’s University, Republic of Korea

Talks

• 2025-06-13    Deep Heaviside Networks and their Augmentations 

   The 4th workshop on Mathematics and AI, University of Tilburg, Netherlands

• 2025-06-05    On the Optimality of Bayesian Neural Networks with Gaussian Priors 

    Academic Seminar, Ruhr University Bochum, Germany

• 2025-05-13    Deep Heaviside networks: from artificial neural networks to biological neural networks

    Academic Seminar, Inha University, Republic of Korea

• 2025-05-07    On the Expressivity of Deep Heaviside Networks 

   Workshop on the Statistical Theory of Neural Networks, Egmond aan Zee, Netherlands

• 2024-12-27    Function approximations using DNNs and applications for statistical learning

    Academic Seminar, Seoul National University, Republic of Korea

• 2024-06-13    A Study on Bayesian Neural Networks and Their Variations

    Academic Seminar, Sookmyung Women’s University, Republic of Korea

• 2024-06-07    Posterior concentrations of fully-connected Bayesian neural networks with general priors on the weights

    Bayesian Statistical Research Society, University of Seoul, Republic of Korea

Award

• 2024-08-29     Best Ph.D. Dissertation Award from the College of Natural Sciences  

    Seoul National University, Republic of Korea

Referee Service

• Annals of Statistics, Bernoulli, Electronic Journal of Statistics, IEEE Transactions on Information Theory