activity
20242026
collaborators

8 papers

cs.LG2026

Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization

Chaewon Moon, Dongkuk Si, Chulhee Yun

We study the implicit bias of Sharpness-Aware Minimization (SAM) when training -layer linear diagonal networks on linearly separable binary classification. For linear models ($L…

cs.LG2026

Implicit Bias and Loss of Plasticity in Matrix Completion: Depth Promotes Low-Rankness

Baekrok Shin, Chulhee Yun

We study matrix completion via deep matrix factorization (a.k.a. deep linear neural networks) as a simplified testbed to examine how network depth influences training dynamics. Des…

cs.LG2026

Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?

Jihwan Kim, Dogyoon Song, Chulhee Yun

We study scaling laws of signSGD under a power-law random features (PLRF) model that accounts for both feature and target decay. We analyze the population risk of a linear model tr…

cs.LG2026

Uniform Spectral Growth and Convergence of Muon in LoRA-Style Matrix Factorization

Changmin Kang, Jihun Yun, Baekrok Shin +2

Spectral gradient descent (SpecGD) orthogonalizes the matrix parameter updates and has inspired practical optimizers such as Muon. They often perform well in large language model (…

cs.LG2025

From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning

Junsoo Oh, Jerry Song, Chulhee Yun

Weak-to-strong generalization refers to the phenomenon where a stronger model trained under supervision from a weaker one can outperform its teacher. While prior studies aim to exp…

cs.LG2025

Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty

Yeseul Cho, Baekrok Shin, Changmin Kang +1

Recent advances in deep learning rely heavily on massive datasets, leading to substantial storage and training costs. Dataset pruning aims to alleviate this demand by discarding re…