Jongyeong Lee

Postdoctoral Researcher (Technical Research Personnel, 전문연) in the Computational Science Research Center at the Korea Institute of Science and Technology (KIST) hosted by Prof. Chansoo Kim.
I am currently looking for next academic positions at universities or research institutes starting after December (when my military duty ends).
If you know of any relevant opportunities, please let me know (not restricted to Korea)!

[Google Scholar] [CV]

Contact: jongyeong [at] kist.re.kr / jongyeong.lee95 [at] gmail.com (in general, gmail is faster)

Research Interests

News

Publications

Conference Proceedings (peer-reviewed, *: equal contribution)

  1. Jongyeong Lee, Junya Honda, Shinji Ito, and Min-hwan Oh,
    "Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems,"
    The 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025), pp. xx-xx, San Diego, USA, Dec. 2-7, 2025.
    [openreview] [poster]
  2. Botao Chen*, Jongyeong Lee*, and Junya Honda,
    "Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems,"
    The 42nd International Conference on Machine Learning (ICML 2025), pp. 8403-8426, Vancouver, Canada, Jul. 13-Jul. 19, 2025.
    [proceeding] [poster by Botao]
  3. Jongyeong Lee, Junya Honda, Shinji Ito, and Min-hwan Oh,
    "Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds,"
    The 37th Annual Conference on Learning Theory (COLT 2024), pp. 3375-3430, Edmonton, Canada, Jun. 30-Jul. 3, 2024.
    [proceeding] [poster] [slides]
  4. Jongyeong Lee, Chao-Kai Chiang, and Masashi Sugiyama,
    "The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models"
    The 38th AAAI Conference on Artificial Intelligence (AAAI 2024), pp. 13383-13390, Vancouver, Canada, Feb. 20-27, 2024.
    Oral [arXiv (full)] [proceeding] [poster] [slides]
  5. Jongyeong Lee, Junya Honda, and Masashi Sugiyama,
    "Thompson Exploration with Best Challenger Rule in Best Arm Identification"
    The 15th Asian Conference on Machine Learning (ACML 2023), pp. 646-661, Istanbul, Turkey, Nov. 11-14, 2023.
    Long Oral [proceeding] [arXiv (Corrigendum)] [poster] [slides]
  6. Jongyeong Lee, Junya Honda, Chao-Kai Chiang, and Masashi Sugiyama,
    "Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits"
    The 40th International Conference on Machine Learning (ICML2023), pp.18810-18851, Hawaii, USA, Jul. 23-29, 2023.
    [proceeding] [poster]
  7. Nontawat Charoenphakdee, Jongyeong Lee, Yiping Jin, Dittaya Wanvarie, and Masashi Sugiyama,
    "Learning Only from Relevant Keywords and Unlabeled Documents"
    The 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP2019), Hong Kong, Nov. 3-7, 2019.
    [proceeding] [more information by Nutt]
  8. Nontawat Charoenphakdee, Jongyeong Lee, and Masashi Sugiyama,
    "On Symmetric Losses for Learning from Corrupted Labels"
    The 36th International Conference on Machine Learning (ICML2019), Long Beach, California, USA, Jun. 9-15, 2019.
    Long Oral [proceeding] [more information by Nutt]

Others (preprints / workshops)

  1. Chaiwon Kim*, Jongyeong Lee*, and Min-hwan Oh,
    “Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality”
    NeurIPS 2025 Workshop MLxOR: Mathematical Foundations and Operational Integration of Machine Learning for Uncertainty-Aware Decision-Making.
    Best Paper Award at KAIA (Korean Artificial Intelligence Association) Fall Conference 2025 (JKAIA 2025).
    [arXiv]
  2. Nontawat Charoenphakdee, Jongyeong Lee, and Masashi Sugiyama,
    “A Symmetric Loss Perspective of Reliable Machine Learning”
    The Fields Institute Communications Series on Data Science and Optimization, 2021.
    An invited article preprint [arXiv]
  3. Jongyeong Lee, Nontawat Charoenphakdee, and Masashi Sugiyama,
    “Domain Discrepancy Measure Using Complex Models in Unsupervised Domain Adaptation”
    Symbolic-Neural Learning Workshop (SNL 2019), 2019.
    [arXiv]

Grants

Education

Work Experiences

Reivewer

© Jongyeong Lee, Jan 25, 2026