Generative model for optimal density estimation on unknown manifold

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Stéphanovitch, Arthur
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913910294052864
author Stéphanovitch, Arthur
author_facet Stéphanovitch, Arthur
contents We propose a generative model that achieves minimax-optimal convergence rates for estimating probability distributions supported on unknown low-dimensional manifolds. Building on Fefferman's solution to the geometric Whitney problem, our estimator is itself supported on a submanifold that matches the regularity of the data's support. This geometric adaptation enables the estimator to be simultaneously minimax-optimal for all \( γ\)-Hölder Integral Probability Metrics (IPMs) with \( γ\geq 1 \). We validate our approach through experiments on synthetic and real datasets, demonstrating competitive or superior performance compared to Wasserstein GAN and score-based generative models.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19587
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative model for optimal density estimation on unknown manifold
Stéphanovitch, Arthur
Statistics Theory
We propose a generative model that achieves minimax-optimal convergence rates for estimating probability distributions supported on unknown low-dimensional manifolds. Building on Fefferman's solution to the geometric Whitney problem, our estimator is itself supported on a submanifold that matches the regularity of the data's support. This geometric adaptation enables the estimator to be simultaneously minimax-optimal for all \( γ\)-Hölder Integral Probability Metrics (IPMs) with \( γ\geq 1 \). We validate our approach through experiments on synthetic and real datasets, demonstrating competitive or superior performance compared to Wasserstein GAN and score-based generative models.
title Generative model for optimal density estimation on unknown manifold
topic Statistics Theory
url https://arxiv.org/abs/2506.19587