A generative flow for conditional sampling via optimal transport

Author name not available (Why is that?)

Publication date: 9 July 2023

Abstract: 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.

Has companion code repository: https://github.com/giuliotrigila/moonexample

This page was built for publication: A generative flow for conditional sampling via optimal transport

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6443063)