Wang, Zhichao
15 publications
NeurIPS
2025
Generalization Bound of Gradient Flow Through Training Trajectory and Data-Dependent Kernel
ICLR
2024
Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models
NeurIPS
2023
Learning in the Presence of Low-Dimensional Structure: A Spiked Random Matrix Perspective
NeurIPS
2022
High-Dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation