Dequantified Diffusion-Schrödinger Bridge for Density Ratio Estimation

Code

• github.com/hoemr/dequantified-diffusion-bridge-density-ratio-estimation
  OfficialIn paperpytorch★ 3

Abstract

Density ratio estimation is fundamental to tasks involving f-divergences, yet existing methods often fail under significantly different distributions or inadequately overlap supports, suffering from the density-chasm and the support-chasm problems. Additionally, prior approaches yield divergent time scores near boundaries, leading to instability. We design D^3RE, 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\"odinger bridge interpolant (DSBI) incorporates optimal transport to solve the Schr\"odinger 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.

Tasks

Reproductions