Joongkyu Lee is a Postdoctoral Research Scholar in the Department of Industrial Engineering and Operations Research at Columbia University, working with Prof. Garud Iyengar and Prof. Assaf Zeevi.

He received his Ph.D. and M.S. in Data Science from Seoul National University, where he was advised by Prof. Min-hwan Oh. He received his B.S. in Industrial Engineering from Yonsei University.

His primary research interests include sequential decision-making, reinforcement learning, bandit algorithms, statistical machine learning, and optimization for machine learning, as well as their practical applications. His ultimate research goal is to develop learning algorithms that are both theoretically principled and practically implementable.

Interests
  • Sequential Decision Making
  • Reinforcement Learning
  • Bandit Algorithms
  • Statistical Machine Learning
  • Optimization
  • Quantization
Academic Appointment
  • Postdoctoral Research Scholar, 2026 - Present

    Columbia University, IEOR

Education
  • Ph.D. in Data Science, 2026

    Seoul National University

  • M.S. in Data Science, 2023

    Seoul National University

  • B.S. in Industrial Engineering, 2016

    Yonsei University

Recent Publications & Preprints

(2026). Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards. arXiv 2026.

PDF

(2026). Block-Sphere Vector Quantization. arXiv 2026.

PDF

(2025). True Impact of Cascade Length in Contextual Cascading Bandits. NeurIPS 2025.

PDF

(2025). Combinatorial Reinforcement Learning with Preference Feedback. ICML 2025.

PDF