3 papers
cs.LG2026
Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling
Yeseul Cho, Baekrok Shin, Changmin Kang +1
Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require full…
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
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…