Data Generation without Function Estimation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Daneshmand, Hadi, Soleymani, Ashkan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912476035022848
author Daneshmand, Hadi
Soleymani, Ashkan
author_facet Daneshmand, Hadi
Soleymani, Ashkan
contents Estimating the score function (or other population-density-dependent functions) is a fundamental component of most generative models. However, such function estimation is computationally and statistically challenging. Can we avoid function estimation for data generation? We propose an estimation-free generative method: A set of points whose locations are deterministically updated with (inverse) gradient descent can transport a uniform distribution to arbitrary data distribution, in the mean field regime, without function estimation, training neural networks, and even noise injection. The proposed method is built upon recent advances in the physics of interacting particles. We show, both theoretically and experimentally, that these advances can be leveraged to develop novel generative methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08239
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data Generation without Function Estimation
Daneshmand, Hadi
Soleymani, Ashkan
Machine Learning
Mathematical Physics
Optimization and Control
Estimating the score function (or other population-density-dependent functions) is a fundamental component of most generative models. However, such function estimation is computationally and statistically challenging. Can we avoid function estimation for data generation? We propose an estimation-free generative method: A set of points whose locations are deterministically updated with (inverse) gradient descent can transport a uniform distribution to arbitrary data distribution, in the mean field regime, without function estimation, training neural networks, and even noise injection. The proposed method is built upon recent advances in the physics of interacting particles. We show, both theoretically and experimentally, that these advances can be leveraged to develop novel generative methods.
title Data Generation without Function Estimation
topic Machine Learning
Mathematical Physics
Optimization and Control
url https://arxiv.org/abs/2507.08239