9 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.…
Generative models for decision-making under distributional shift
Xiuyuan Cheng, Yunqin Zhu, Yao Xie
Many data-driven decision problems are formulated using a nominal distribution estimated from historical data, while performance is ultimately determined by a deployment distributi…
Learning manifold diffusion semigroups from graph transition matrices
Xiuyuan Cheng, Nan Wu
We consider graph diffusion processes constructed from finite i.i.d. samples drawn from an unknown manifold embedded in ambient Euclidean space, where the graph affinity is defined…
Point processes with event time uncertainty
Xiuyuan Cheng, Tingnan Gong, Yao Xie
Point processes are widely used statistical models for continuous-time discrete event data, such as medical records, crime reports, and social network interactions, to capture the…
Worst-case generation via minimax optimization in Wasserstein space
Xiuyuan Cheng, Yao Xie, Linglingzhi Zhu +1
Worst-case generation plays a critical role in evaluating robustness and stress-testing systems under distribution shifts, in applications ranging from machine learning models to p…
High-dimensional Mean-Field Games by Particle-based Flow Matching
Jiajia Yu, Junghwan Lee, Yao Xie +1
Mean-field games (MFGs) study the Nash equilibrium of systems with a continuum of interacting agents, which can be formulated as the fixed-point of optimal control problems. They p…