A generative flow for conditional sampling via optimal transport

作者：Jason Alfonso, R. Baptista, Anupam Bhakta, N. Gal, Alfin Hou, I. Lyubimova, Daniel Pocklington, Josef Sajonz, G. Trigila, Ryan Tsai · 发表于：arXiv.org · 年份：2023 · DOI：10.48550/arxiv.2307.04102 · 被引用次数：7 · 研究领域：Mathematics、Computer Science

Sampling conditional distributions is a fundamental task for Bayesian inference and density estimation. Generative models, such as normalizing flows and generative adversarial networks, characterize conditional distributions by learning a transport map that pushes forward a simple reference (e.g., a standard Gaussian) to a target distribution. While these approaches successfully describe many non-Gaussian problems, their performance is often limited by parametric bias and the reliability of gradient-based (adversarial) optimizers to learn these transformations. This work proposes a non-parametric generative model that iteratively maps reference samples to the target. The model uses block-triangular transport maps, whose components are shown to characterize conditionals of the target distribution. These maps arise from solving an optimal transport problem with a weighted $L^2$ cost function, thereby extending the data-driven approach in [Trigila and Tabak, 2016] for conditional sampling. The proposed approach is demonstrated on a two dimensional example and on a parameter inference problem involving nonlinear ODEs.