Showing 2026Show all
2 papers · 1 filter
stat.ME2026
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…
stat.ML2026
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…