Minhak Song

According to our database, Minhak Song authored at least 10 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

AMUSE: Anytime Muon with Stable Gradient Evaluation.

Jueun Kim, Baekrok Shin, Jihun Yun, Beomhan Baek, Minhak Song, Chulhee Yun

CoRR, May, 2026

Zeroth-Order Optimization at the Edge of Stability.

Minhak Song, Liang Zhang, Bingcong Li, Niao He, Michael Muehlebach, Sewoong Oh

CoRR, April, 2026

Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis.

Shenyang Deng, Boyao Liao, Zhuoli Ouyang, Tianyu Pang, Minhak Song, Yaoqing Yang

CoRR, January, 2026

2025

Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime.

Beomhan Baek, Minhak Song, Chulhee Yun

CoRR, October, 2025

Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO.

Ruizhe Shi, Minhak Song, Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du

CoRR, May, 2025

Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training.

Minhak Song, Beomhan Baek, Kwangjun Ahn, Chulhee Yun

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More.

Geonhui Yoo, Minhak Song, Chulhee Yun

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Does SGD really happen in tiny subspaces?

Minhak Song, Kwangjun Ahn, Chulhee Yun

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Linear attention is (maybe) all you need (to understand Transformer optimization).

Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory.

Minhak Song, Chulhee Yun

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023