Hanseul Cho

Hanseul Cho

PhD Student at OptiML Lab in KAIST AI. Working on ML/DL/Opt+Theory and LMs.

Welcome!

My name is Hanseul Cho(์กฐํ•œ์Šฌ). I am a Ph.D. student in the Optimization & Machine Learning (OptiML) Laboratory, advised by Prof. Chulhee Yun at Kim Jaechul Graduate School of AI in Korea Advanced Institute of Science and Technology (KAIST AI).

๐ŸšจI am Looking for Internship Opportunitiesโ€ผ๏ธ๐Ÿšจ

I am interested in a broad range of fields in optimization, machine learning (ML), and deep learning (DL), especially focusing on both mathematical/theoretical analysis and empirical improvements (usually based on theoretical understanding). Recently, I have been into understanding and mitigating the fundamental limitations of modern language models (e.g., length generalization and compositional generalization problems). Also, I am always interested in hierarchical/multi-level optimization (e.g., minimax optimization), optimization with constraints (e.g., fairness in ML), optimization under circumstance shifts (e.g., reinforcement learning and continual learning).

๐Ÿ“ฐ Publications ๐Ÿ“ฐ

Please click the โ€œPublicationโ€ tab above to look up the full list of my publications.
You can also find my articles on my Google Scholar profile.

โ€ผ๏ธNewsโ€ผ๏ธ

  • ๐Ÿ—ž๏ธ [Nov. '24] Our paper on theoretical analysis of continual learning is accepted to JKAIA 2024 and won the Best Paper Award! ๐ŸŽ‰ (See Publications for more details)
  • ๐Ÿ—ž๏ธ [Nov. '24] I'm selected as one of the Top Reviewers (top 8.6%: 1,304 of 15,160 reviewers) at NeurIPS 2024! (+ Free registration! ๐Ÿ˜Ž)
  • ๐Ÿ—ž๏ธ [Sep. '24] Two papers got accepted to NeurIPS 2024! ๐ŸŽ‰ One is about length generalization of arithmetic Transfomers, and another is about mitigating loss of plasticity in incremental neural net training. See you in Vancouver๐Ÿ‡จ๐Ÿ‡ฆ!
  • ๐Ÿ—ž๏ธ [Jun. '24] An early version of our paper on length generalization of Transformers got accepted to the ICML 2024 Workshop on Long-Context Foundation Models!
  • ๐Ÿ—ž๏ธ [May. '24] A paper got accepted to ICML 2024 as a spotlight paper (top 3.5% among all submissions)! ๐ŸŽ‰ We show global convergence of Alt-GDA (which is strictly faster than Sim-GDA) and propose an enhanced algorithm called Alex-GDA for minimax optimization. See you in Vienna๐Ÿ‡ฆ๐Ÿ‡น!
  • ๐Ÿ—ž๏ธ [Sep. '23] Two papers are accepted to NeurIPS 2023! ๐ŸŽ‰ One is about Fair Streaming PCA and another is about enhancing plasticity in RL.
  • ๐Ÿ—ž๏ธ [Jan. '23] Our paper about shuffling-based stochastic gradient descent-ascent got accepted to ICLR 2023!
  • ๐Ÿ—ž๏ธ [Nov. '22] Our paper about shuffling-based stochastic gradient descent-ascent is accepted to 2022 Korea AI Association + NAVER Autumnal Joint Conference (JKAIA 2022) and selected as the NAVER Outstanding Theory Paper!
  • ๐Ÿ—ž๏ธ [Oct. '22] I am happy to announce that our very first preprint is now on arXiv! It is about convergence analysis of shuffling-based stochastic gradient descent-ascent.
  • ๐Ÿ—ž๏ธ [Feb. '22] Now I am part of OptiML Lab of KAIST AI.

Education

  • ๐Ÿซ Ph.D. in Artificial Intelligence KAIST, Sept. 2023 โ€“ Current
  • ๐Ÿซ M.Sc. in Artificial Intelligence KAIST, Mar. 2022 โ€“ Aug. 2023
  • ๐Ÿซ B.Sc. in Mathematical Sciences KAIST, Mar. 2017 โ€“ Feb. 2022
    • Minor in Computing Sciences / Summa Cum Laude

Contact & Info

๐Ÿ“‹ Curriculum Vitae (CV): Here
๐Ÿ“ง Email: jhs4015 at kaist dot ac dot kr