Jihwan Kim
I am an undergraduate at Seoul National University interested in deep learning theory and practice, especially optimizer theory (scaling laws and optimization dynamics), efficient optimizers for large language model training, and privacy in ML and LLMs.
news
| May 01, 2026 | Our paper on Ski Rental with Distributional Advice is accepted at ICML 2026. |
|---|---|
| Jan 26, 2026 | Our paper on Scaling Law of SignSGD is accepted at ICLR 2026. |
selected publications
- ICMLRobust and Consistent Ski Rental with Distributional AdviceIn Forty-Third International Conference on Machine Learning, 2026
- ICLRScaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?In The Fourteenth International Conference on Learning Representations, 2026