2 papers
stat.ME2026
Principled Inference in Dense High-Dimensional Linear Models via Local Conditional Sparsity
Wenjun Xiong, Yan Chen, Mingya Long +1
High-dimensional inference methods often rely on coefficient sparsity, an assumption that can be restrictive when signals are dense but individually weak. In such settings, valid i…
stat.ML2025
Tight Generalization Error Bounds for Stochastic Gradient Descent in Non-convex Learning
Wenjun Xiong, Juan Ding, Xinlei Zuo +1
Stochastic Gradient Descent (SGD) is fundamental for training deep neural networks, especially in non-convex settings. Understanding SGD's generalization properties is crucial for…