2 papers
cs.LG2025
Memorizing Long-tail Data Can Help Generalization Through Composition
Mo Zhou, Haoyang Ma, Rong Ge
Deep learning has led researchers to rethink the relationship between memorization and generalization. In many settings, memorization does not hurt generalization due to implicit r…
cs.LG2024
How Does Gradient Descent Learn Features -- A Local Analysis for Regularized Two-Layer Neural Networks
Mo Zhou, Rong Ge
The ability of learning useful features is one of the major advantages of neural networks. Although recent works show that neural network can operate in a neural tangent kernel (NT…