From the 1 of 7 linked papers with an AI index.
7 papers
AMUSE: Anytime Muon with Stable Gradient Evaluation
Jueun Kim, Baekrok Shin, Jihun Yun +3
The paper introduces AMUSE, an optimization method that combines Muon's orthogonal momentum updates with Schedule-Free iterate averaging to achieve fast, stable training without le…
Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
Ruizhe Shi, Minhak Song, Runlong Zhou +3
We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and direct preference optimization~(DPO).…
Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis
Shenyang Deng, Boyao Liao, Zhuoli Ouyang +3
This paper explores the suspicious alignment phenomenon in stochastic gradient descent (SGD) under ill-conditioned optimization, where the Hessian spectrum splits into dominant and…
Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
Beomhan Baek, Minhak Song, Chulhee Yun
Adam [Kingma & Ba, 2015] is the de facto optimizer in deep learning, yet its theoretical understanding remains limited. Prior analyses show that Adam favors solutions aligned with…
Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
Minhak Song, Beomhan Baek, Kwangjun Ahn +1
As both model and dataset sizes continue to scale rapidly, conventional pretraining strategies with fixed compute budgets-such as cosine learning rate schedules-are increasingly in…
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
When training deep neural networks with gradient descent, sharpness often increases -- a phenomenon known as progressive sharpening -- before saturating at the edge of stability. A…