Saved in:
Bibliographic Details
Main Authors: Kwon, Hyeok Kyu, Chae, Minwoo
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.06755
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929237394456576
author Kwon, Hyeok Kyu
Chae, Minwoo
author_facet Kwon, Hyeok Kyu
Chae, Minwoo
contents A deep generative model yields an implicit estimator for the unknown distribution or density function of the observation. This paper investigates some statistical properties of the implicit density estimator pursued by VAE-type methods from a nonparametric density estimation framework. More specifically, we obtain convergence rates of the VAE-type density estimator under the assumption that the underlying true density function belongs to a locally Hölder class. Remarkably, a near minimax optimal rate with respect to the Hellinger metric can be achieved by the simplest network architecture, a shallow generative model with a one-dimensional latent variable.
format Preprint
id arxiv_https___arxiv_org_abs_2305_06755
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Minimax optimal density estimation using a shallow generative model with a one-dimensional latent variable
Kwon, Hyeok Kyu
Chae, Minwoo
Statistics Theory
A deep generative model yields an implicit estimator for the unknown distribution or density function of the observation. This paper investigates some statistical properties of the implicit density estimator pursued by VAE-type methods from a nonparametric density estimation framework. More specifically, we obtain convergence rates of the VAE-type density estimator under the assumption that the underlying true density function belongs to a locally Hölder class. Remarkably, a near minimax optimal rate with respect to the Hellinger metric can be achieved by the simplest network architecture, a shallow generative model with a one-dimensional latent variable.
title Minimax optimal density estimation using a shallow generative model with a one-dimensional latent variable
topic Statistics Theory
url https://arxiv.org/abs/2305.06755