4 papers
Local Flow Matching Generative Models
Chen Xu, Xiuyuan Cheng, Yao Xie
Flow Matching (FM) is a simulation-free method for learning a continuous, invertible flow that interpolates between two distributions, and in particular generates data from noise.…
Flow-based Conformal Prediction for Multi-dimensional Time Series
Junghwan Lee, Chen Xu, Yao Xie
Time series prediction underpins a broad range of downstream tasks across many scientific domains. Recent advances and increasing adoption of black-box machine learning models for…
Kernel-based Optimally Weighted Conformal Time-Series Prediction
Jonghyeok Lee, Chen Xu, Yao Xie
In this work, we present a novel conformal prediction method for time-series, which we call Kernel-based Optimally Weighted Conformal Prediction Intervals (KOWCPI). Specifically, K…
Computing high-dimensional optimal transport by flow neural networks
Chen Xu, Xiuyuan Cheng, Yao Xie
Computing optimal transport (OT) for general high-dimensional data has been a long-standing challenge. Despite much progress, most of the efforts including neural network methods h…