4 papers
Smoothed-KL Reweighting: A Principled Account and Matching Rule for SNR-Based Diffusion Training
Lei Li
We give a principled derivation of the Soft-Min-SNR weight of Crowson et al. (2024). The spread divergence of Zhang et al. (2018) convolves both compared distributions with a Gauss…
A Generative Sampler for distributions with possible discrete parameter based on Reversibility
Lei Li, Zhen Wang, Lishuo Zhang
Learning to sample from complex unnormalized distributions is a fundamental challenge in computational physics and machine learning. While score-based and variational methods have…
Solving Schrödinger bridge problem via continuous normalizing flow
Yang Jing, Lei Li, Jingtong Zhang
The Schrödinger Bridge Problem (SBP), which can be understood as an entropy-regularized optimal transport, seeks to compute stochastic dynamic mappings connecting two given distrib…
Solving stationary nonlinear Fokker-Planck equations via sampling
Lei Li, Yijia Tang, Jingtong Zhang
Solving the stationary nonlinear Fokker-Planck equations is important in applications and examples include the Poisson-Boltzmann equation and the two layer neural networks. Making…