Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
Learning with Synthetic Data via SGD in High-Dimensional Linear Regression
Jichu li, Difan Zou
Synthetic data has become a promising way to scale model training beyond limited human-generated data but it may also induce strong model collapse (Dohmatob et al., 2024), where an…
stat.ML2026
A Mechanism Study of Delayed Loss Spikes in Batch-Normalized Linear Models
Peifeng Gao, Wenyi Fang, Yang Zheng +1
Delayed loss spikes have been reported in neural-network training, but existing theory mainly explains earlier non-monotone behavior caused by overly large fixed learning rates. We…
stat.ML2026
Scaling Laws for Precision in High-Dimensional Linear Regression
Dechen Zhang, Xuan Tang, Yingyu Liang +1
Low-precision training is critical for optimizing the trade-off between model quality and training costs, necessitating the joint allocation of model size, dataset size, and numeri…