Dequantified Diffusion-Schrödinger Bridge for Density Ratio Estimation
Wei Chen, Shigui Li, Jiacheng Li, Junmei Yang, John Paisley, Delu Zeng
Abstract
Density ratio estimation is fundamental to tasks involving f-divergences, yet existing methods often fail under significantly different distributions or inadequately overlapping supports --- the density-chasm and the support-chasm problems. Additionally, prior approaches yield divergent time scores near boundaries, leading to instability. We design $\textbf{D}^3\textbf{RE}$, a unified framework for robust, stable and efficient density ratio estimation. We propose the dequantified diffusion bridge interpolant (DDBI), which expands support coverage and stabilizes time scores via diffusion bridges and Gaussian dequantization. Building on DDBI, the proposed dequantified Schr{\"o}dinger bridge interpolant (DSBI) incorporates optimal transport to solve the Schr{\"o}dinger bridge problem, enhancing accuracy and efficiency. Our method offers uniform approximation and bounded time scores in theory, and outperforms baselines empirically in mutual information and density estimation tasks.
BibTeX
@inproceedings{
chen2025dequantified,
title={Dequantified Diffusion-Schr\"odinger Bridge for Density Ratio Estimation},
author={Wei Chen and Shigui Li and Jiacheng Li and Junmei Yang and John Paisley and Delu Zeng},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=zvyHCOcwsw}
}