2 papers
stat.ML2025
Trajectory Inference with Smooth Schrödinger Bridges
Wanli Hong, Yuliang Shi, Jonathan Niles-Weed
Motivated by applications in trajectory inference and particle tracking, we introduce Smooth Schrödinger Bridges. Our proposal generalizes prior work by allowing the reference proc…
stat.ML2024
Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data
Wanli Hong, Shuyang Ling
Neural collapse (NC) is a phenomenon that emerges at the terminal phase of the training (TPT) of deep neural networks (DNNs). The features of the data in the same class collapse to…