Kyoungseok Jang

Assistant Professor at Chung-Ang University

I am an assistant professor working at Chung-Ang University. Before this, I did my postdoc with Prof. Nicolò Cesa-Bianchi at Università degil Studi di Milano, Prof. Komiyama Junpei at NYU, and Prof. Kwang-Sung Jun at the University of Arizona. I got my Ph.D. in the Department of Mathematical Science at KAIST (Korea Advanced Institute of Science and Technology) with the advisor Wanmo Kang.

My research interests lie in statistical machine-learning problems, such as
  • Reinforcement learning (bandit)
    • High-dimensional bandits (sparse, bilinear, etc.)
    • Best arm identification
  • Generalization bounds (PAC-Bayes bound)
  • Generative model (GAN, VAE)
  • Other probabilistic tools (Stochastic PDE, Random Matrix Theory, etc......)

CV link

  • A new (spotlight) paper at ICML 2025!

    Posted on May 2, 2025

    Title: GL-LowPopArt: A Nearly Instance-Wise Minimax Estimator for (Adaptive) Generalized Linear Low-Rank Trace Regression Authors: Junghyun Lee, Kyoungseok Jang, Kwang-Sung Jun, Milan Vojnovic, Se-Young Yun [Read More]

  • Looking for Ph.D. students

    Posted on March 1, 2025

    I am looking for students to work with me on research in statistical learning and reinforcement learning. If you are interested, feel free to contact me at ksjang@cau.ac.kr.

  • A new paper at ICML 2024!

    Posted on July 23, 2024

    Title: Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits Authors: Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun Link to the paper [Read More]

  • A new paper at COLT 2024!

    Posted on July 1, 2024

    Title: Tighter PAC-Bayes Bounds Through Coin-Betting Authors: Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona Link to the paper [Read More]