One paper accepted to NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning (M3L) as an *oral presentation*!
Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study
One paper (Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study) is accepted to NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning (M3L) as an oral presentation! This is joint work with the wonderful undergradudate intern Prin Phunyaphibarn (KAIST Math, equal contributions), my advisor Chulhee Yun (KAIST AI), and collaborators Bohan Wang (USTC) and Huishuai Zhang (Microsoft Research Asia - Theory Centre).
I’ll be attending and presenting in person. See you all at New Orleans, USA!
Junghyun Lee
PhD Student
PhD student at GSAI, KAIST, jointly advised by Prof. Se-Young Yun and Prof. Chulhee Yun. Interested in mathematical and theoretical AI, i.e., essentially any machine learning challenges necessitating mathematical analysis. Recently focused on statistical problems arising from RLHF, including interactive machine learning and low-dimensional structure recovery.