ML Anthology
Authors
Search
About
Song, Minhak
7 publications
ICLR
2025
Does SGD Really Happen in Tiny Subspaces?
Minhak Song
,
Kwangjun Ahn
,
Chulhee Yun
NeurIPS
2025
Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
Minhak Song
,
Beomhan Baek
,
Kwangjun Ahn
,
Chulhee Yun
ICML
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
ICMLW
2024
Does SGD Really Happen in Tiny Subspaces?
Minhak Song
,
Kwangjun Ahn
,
Chulhee Yun
ICLR
2024
Linear Attention Is (maybe) All You Need (to Understand Transformer Optimization)
Kwangjun Ahn
,
Xiang Cheng
,
Minhak Song
,
Chulhee Yun
,
Ali Jadbabaie
,
Suvrit Sra
NeurIPSW
2023
Linear Attention Is (maybe) All You Need (to Understand Transformer Optimization)
Kwangjun Ahn
,
Xiang Cheng
,
Minhak Song
,
Chulhee Yun
,
Ali Jadbabaie
,
Suvrit Sra
NeurIPS
2023
Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory
Minhak Song
,
Chulhee Yun