Welcome!
My name is Hanseul Cho(μ‘°νμ¬). 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).
π¨I am Looking for Internship OpportunitiesβΌοΈπ¨
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).
News
- π° [Sep. '24] Two papers got accepted to NeurIPS 2024! π One is about length generalization of arithmetic Transfomers, and another is about mitigating loss of plasticity in incremental neural net training. See you in Vancouverπ¨π¦!
- π° [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!
- π° [May. '24] A paper got accepted to ICML 2024 as a spotlight paper (top 3.5% among all submissions)! π 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 Viennaπ¦πΉ!
- π° [Sep. '23] Two papers are accepted to NeurIPS 2023! π One is about Fair Streaming PCA and another is about enhancing plasticity in RL.
- π° [Jan. '23] Our paper about shuffling-based stochastic gradient descent-ascent got accepted to ICLR 2023! π
- π° [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!
- π° [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.
- π° [Feb. '22] Now I am part of OptiML Lab of KAIST AI.
Education
- π« Ph.D. in Artificial Intelligence
KAIST, Sept. 2023 - Current - π« M.Sc. in Artificial Intelligence
KAIST, Mar. 2022 - Aug. 2023 - π« B.Sc. in Mathematical Sciences
KAIST, Mar. 2017 - Feb. 2022 - Minor in Computing Sciences / Summa Cum Laude
Contact & Info
π Curriculum Vitae: Here
π§ Email address: jhs4015 at kaist dot ac dot kr