avatar

Minhak Song

Undergraduate Student
KAIST
minhaksong (at) kaist.ac.kr


About Me

Hi! I am an undergraduate student at KAIST, double majoring in Industrial & Systems Engineering and Mathematical Sciences. My research interest lies in building the theoretical foundations of modern machine learning through the lens of optimization theory and statistics. Recently, I am focusing on understanding the training dynamics of gradient-based optimization methods in deep learning, closely working with Prof. Chulhee Yun. Feel free to reach out for discussions and potential collaborations!

Currently, I am on a leave of absence from KAIST to complete my mandatory military service in South Korea, which will last from February 2023 to November 2024.

Research Interests

News

Publications

  1. Minhak Song, Kwangjun Ahn, Chulhee Yun
    Manuscript, 2024.
    ICML 2024 Workshop on High-dimensional Learning Dynamics: The Emergence of Structure and Reasoning.
  2. Kwangjun Ahn*, Xiang Cheng*, Minhak Song*, Chulhee Yun, Ali Jadbabaie, Suvrit Sra
    (*Equal contribution)
    International Conference on Learning Representations (ICLR), 2024.
    NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning (Oral).
  3. Minhak Song, Chulhee Yun
    Neural Information Processing Systems (NeurIPS), 2023.

Services

Conference Reviewer