Kyurae Kim

profile.jpg

I am a fourth year PhD student (on leave) advised by Professor Jacob R. Gardner at the University of Pennsylvania working on Bayesian computation, stochastic optimization, and Markov chain Monte Carlo.

I acquired my Bachelor in Engineering degree at Sogang University, South Korea, during which I did undergraduate research under Professor Hongseok Kim, Tai-kyong Song, Sungyong Park, and Youngjae Kim. During this time, I also worked at Samsung Medical Center, South Korea, as an undergraduate researcher, at Kangbuk Samsung Hospital, South Korea, as a visiting researcher, and at Hansono, South Korea, as a part-time embedded software engineer. After graduating, I was a research associate at the University of Liverpool under Professor Simon Maskell and Jason F. Ralph.

Previously, I used to work on medical imaging, computer systems, high-performance computing, and array signal processing, but I’m also broadly interested in topics in statistics and optimization. Here is a list of papers that I found interesting over my career.

Software

I am active within Julia’s computational statistics community as part of the Turing language team.

productivity tools that I use

(Last updated in 3 February 2025)
I heavily use cross-platform opensource software tools.

news

Jul 4, 2026 Our analysis of kinetic Langevin Monte Carlo has been accepted to EJS
May 1, 2026 My latest paper on BBVI have been accepted to ICML’26. See you all in Seoul!
Sep 18, 2025 1 paper on BBVI and 1 paper on BayesOpt have been accepted to NeurIPS’25
May 1, 2025 Our paper on tuning SMC samplers have been accepted to ICML’25.
Oct 26, 2024 I will be back in South Korea from December 6 to December 25.

selected publications

  1. Analysis of kinetic Langevin Monte Carlo under the stochastic exponential Euler discretization from underdamped all the way to overdamped
    Kyurae Kim, Samuel Gruffaz, Ji Won Park, and Alain Oliviero Durmus.
    Electronic Journal of Statistics Jul 2026
  2. Stochastic gradient variational inference with second-order gradient estimators from Bures–Wasserstein to parameter space
    Kyurae Kim, Qiang Fu, Yi-An Ma, Jacob R. Gardner, and Trevor Campbell.
    In Proceedings of the International Conference on Machine Learning Jul 2026
  3. Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference
    Kyurae Kim, Yi-An Ma, Trevor Campbell, and Jacob R. Gardner.
    In Advances in Neural Information Processing Systems Dec 2025
  4. Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence Minimization
    Kyurae Kim*, Zuheng Xu*, Jacob R. Gardner, and Trevor Campbell.
    In Proceedings of the International Conference on Machine Learning Jul 2025
  5. Approximation-Aware Bayesian Optimization
    Natalie Maus,  Kyurae Kim, Geoff Pleiss, David Eriksson, John P. Cunningham, and Jacob R. Gardner.
    In Advances in Neural Information Processing Systems Dec 2024
    Link
  6. Provably Scalable Black-Box Variational Inference with Structured Variational Families
    Joohwan Ko*, Kyurae Kim*, Woo Chang Kim, and Jacob R Gardner.
    In Proceedings of the International Conference on Machine Learning (ICML) Jul 2024
    Link
  7. Stochastic Approximation with Biased MCMC for Expectation-Maximization
    Samuel Gruffaz,  Kyurae Kim, Alain Durmus, and Jacob R Gardner.
    In Proceedings of the International Conference on Artificial Intelligence and Machine Learning (AISTATS) May 2024
    Link
  8. Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?
    Kyurae Kim, Yi-An Ma, and Jacob R. Gardner.
    In Proceedings of the International Conference on Artificial Intelligence and Machine Learning (AISTATS) May 2024
    Link
  9. On the Convergence of Black-Box Variational Inference
    Kyurae Kim, Jisu Oh, Kaiwen Wu, Yi-An Ma, and Jacob R. Gardner.
    In Advances in Neural Information Processing Systems Dec 2023
    Link
  10. The Behavior and Convergence of Local Bayesian Optimization
    Kaiwen Wu,  Kyurae Kim, Roman Garnett, and Jacob R. Gardner.
    In Advances in Neural Information Processing Systems Dec 2023
    Link