Jiseok Chae

E2-1, #3227

291 Daehak-ro, Yuseong-gu

Daejeon, Republic of Korea

I am an integrated M.S./Ph.D. student in the Department of Mathematical Sciences, KAIST. My academic advisor is Prof. Donghwan Kim. Previously, I completed my Bachelor’s degree in Mathematical Sciences with minoring Computer Science in KAIST.

I study optimization theory and algorithms for machine learning. Recently, I also got interested in how optimization methods work in real world machine learning applications (implicit biases, generalization properties, etc.). If you are interested in collaborating with me, or if you want to know more about anything that is on this website, feel free to contact me by email.

News

Jun 9, 2025	One paper got accepted to the 3rd Workshop on High-dimensional Learning Dynamics, in ICML 2025.
Apr 29, 2025	I will be presenting at ICCOPT 2025. See you in Los Angeles!
Sep 26, 2024	One paper got accepted to NeurIPS 2024. See you in Vancouver!

Selected publications

2024

NeurIPS

Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements

Jiseok Chae, Chulhee Yun, and Donghwan Kim

The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024

arXiv Bib

@article{Chae24SEG,
  title = {Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements},
  author = {Chae, Jiseok and Yun, Chulhee and Kim, Donghwan},
  journal = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year = {2024},
}

ICLR

Two-timescale Extragradient for Finding Local Minimax Points

Jiseok Chae, Kyuwon Kim, and Donghwan Kim

The Twelfth International Conference on Learning Representations, 2024

arXiv Bib

@article{Chae24two,
  title = {Two-timescale Extragradient for Finding Local Minimax Points},
  author = {Chae, Jiseok and Kim, Kyuwon and Kim, Donghwan},
  journal = {The Twelfth International Conference on Learning Representations},
  year = {2024},
}