Dequantified Diffusion-Schr{ö}dinger Bridge for Density Ratio Estimation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915590780747776 |
|---|---|
| author | Chen, Wei Li, Shigui Li, Jiacheng Yang, Junmei Paisley, John Zeng, Delu |
| author_facet | Chen, Wei Li, Shigui Li, Jiacheng Yang, Junmei Paisley, John Zeng, Delu |
| contents | 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 \textbf{robust}, \textbf{stable} and \textbf{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{ö}dinger bridge interpolant (DSBI) incorporates optimal transport to solve the Schr{ö}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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05034 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dequantified Diffusion-Schr{ö}dinger Bridge for Density Ratio Estimation Chen, Wei Li, Shigui Li, Jiacheng Yang, Junmei Paisley, John Zeng, Delu Machine Learning 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 \textbf{robust}, \textbf{stable} and \textbf{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{ö}dinger bridge interpolant (DSBI) incorporates optimal transport to solve the Schr{ö}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. |
| title | Dequantified Diffusion-Schr{ö}dinger Bridge for Density Ratio Estimation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.05034 |