Shunta Akiyama

On Learnability via Gradient Method for Two-Layer ReLU Neural Networks\n in Teacher-Student Setting

2021 · arXiv (Cornell University)

Deep learning empirically achieves high performance in many applications, but\nits training dynamics has not been fully understood theoretically. In this\npaper, we explore theoretical analysis on training two-layer ReLU neural\nnetworks in a teacher-student regression model, in …