A Deep Generative Approach to Conditional Sampling

doi:10.1080/01621459.2021.2016424

Return

A Deep Generative Approach to Conditional Sampling

2022-02-03

Xingyu Zhou

Yuling Jiao

Jin Liu

Prof. Huang Jian (Jian Huang) *

DOI：10.1080/01621459.2021.2016424

Original

Original request for help

Save

Abstract

En 中文

We propose a deep generative approach to sampling from a conditional distribution based on a unified formulation of conditional distribution and generalized nonparametric regression function using the noise-outsourcing lemma. The proposed approach aims at learning a conditional generator, so that a random sample from the target conditional distribution can be obtained by transforming a sample drawn from a reference distribution. The conditional generator is estimated nonparametrically with neural networks by matching appropriate joint distributions using the Kullback-Liebler divergence. An appealing aspect of our method is that it allows either of or both the predictor and the response to be high-dimensional and can handle both continuous and discrete type predictors and responses. We show that the proposed method is consistent in the sense that the conditional generator converges in distribution to the underlying conditional distribution under mild conditions. Our numerical experiments with simulated and benchmark image data validate the proposed method and demonstrate that it outperforms several existing conditional density estimation methods. Supplementary materials for this article are available online.

Keywords:

Distribution matching

Generative learning

High-dimensional data

Neural networks

Nonparametric estimation