44 citations · 117 across the 31 of their papers we have counts for
6 papers · 1 filter
Scale-Adaptive Generative Flows for Multiscale Scientific Data
Yifan Chen, Eric Vanden-Eijnden
Flow-based generative models can face numerical challenges on scientific data with multiscale Fourier spectra, often producing large errors at fine scales. We approach this problem…
Lipschitz-Guided Design of Interpolation Schedules in Generative Models
Yifan Chen, Eric Vanden-Eijnden, Jiawei Xu
We study the design of interpolation schedules in flow and diffusion-based generative models from both statistical and numerical perspectives. Within the stochastic interpolants fr…
Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed +1
The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high-dimensional settings. However, existing analyses of the algorithm for stron…
Gaussian Measures Conditioned on Nonlinear Observations: Consistency, MAP Estimators, and Simulation
Yifan Chen, Bamdad Hosseini, Houman Owhadi +1
The article presents a systematic study of the problem of conditioning a Gaussian random variable on nonlinear observations of the form where $ϕ: \mathcal{X} \to…
Sampling via Gradient Flows in the Space of Probability Measures
Yifan Chen, Daniel Zhengyu Huang, Jiaoyang Huang +2
Sampling a target probability distribution with an unknown normalization constant is a fundamental challenge in computational science and engineering. Recent work shows that algori…
Gradient Flows for Sampling: Mean-Field Models, Gaussian Approximations and Affine Invariance
Yifan Chen, Daniel Zhengyu Huang, Jiaoyang Huang +2
Sampling a probability distribution with an unknown normalization constant is a fundamental problem in computational science and engineering. This task may be cast as an optimizati…