A Deep Generative Approach to Conditional Sampling
From MaRDI portal
Publication:6077577
Abstract: 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 the action of the conditional generator on 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.
Cites work
- 10.1162/153244303321897690
- A crossvalidation method for estimating conditional densities
- Adaptive approximation and generalization of deep neural network with intrinsic dimensionality
- Approximating conditional distribution functions using dimension reduction
- Converting high-dimensional regression to high-dimensional conditional density estimation
- Deep learning
- Deep network approximation characterized by number of neurons
- Dual representation of \(\phi\)-divergences and applications.
- Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
- Estimation of conditional densities and sensitivity measures in nonlinear dynamical systems
- Exchangeable random measures
- scientific article; zbMATH DE number 1713116 (Why is no real title available?)
- scientific article; zbMATH DE number 1220060 (Why is no real title available?)
- scientific article; zbMATH DE number 2135362 (Why is no real title available?)
- scientific article; zbMATH DE number 837911 (Why is no real title available?)
- scientific article; zbMATH DE number 7064043 (Why is no real title available?)
- scientific article; zbMATH DE number 3320765 (Why is no real title available?)
- scientific article; zbMATH DE number 3322635 (Why is no real title available?)
- Kernel and nearest-neighbor estimation of a conditional quantile
- Nonparametric estimation of a conditional density
- Nonparametric regression on low-dimensional manifolds using deep ReLU networks: function approximation and statistical recovery
- On deep learning as a remedy for the curse of dimensionality in nonparametric regression
- On the rate of convergence of fully connected deep neural network regression estimates
- Pattern recognition and machine learning.
- Rejoinder: ``Nonparametric regression using deep neural networks with ReLU activation function
- Sliced Inverse Regression for Dimension Reduction
- Weak convergence and empirical processes. With applications to statistics
Cited in
(16)- scientific article; zbMATH DE number 7403502 (Why is no real title available?)
- Quasi-Random Sampling for Multivariate Distributions via Generative Neural Networks
- An Acceleration Strategy for Randomize-Then-Optimize Sampling Via Deep Neural Networks
- Individualized causal mediation analysis with continuous treatment using conditional generative adversarial networks
- Implicit generative prior for Bayesian neural networks
- Deep quantile sequential generative framework for high-density data generation
- Wasserstein GAN-based estimation for conditional distribution function with current status data
- Wasserstein generative regression
- Deep Mutual Density Ratio Estimation with Bregman Divergence and Its Applications
- Phase-Type Distributions for Sieve Estimation
- Schrödinger bridge based deep conditional generative learning
- Generative Quantile Regression with Variability Penalty
- Conditional optimal transport on function spaces
- Generative semi-supervised classification
- Density estimation and conditional density estimation via a least squares reconstruction method
- A semiparametric generative model for efficient structured-output supervised learning
This page was built for publication: A Deep Generative Approach to Conditional Sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6077577)
