Provably Improving Generalization of Few-Shot Models with Synthetic Data
Published in International Conference on Machine Learning (ICML), 2025
The paper provides a theoretical-guided method for few-shot learning.
Publications
You can also find my articles on my Google Scholar profile. You can click on each paper hyperlink for more details., including code link and slides.
Conference Papers
DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle
Published in International Conference on Learning Representations (ICLR), 2025
Our paper proposed a differentiable pruning at initialization methods that achived significantly better performance on pruning at initialization tasks.