Finite Sample Bounds for Learning with Score Matching

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Smedira, Devin, Jayakumar, Abhijith, Misra, Sidhant, Vuffray, Marc, Lokhov, Andrey Y.
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914565031198720
author Smedira, Devin
Jayakumar, Abhijith
Misra, Sidhant
Vuffray, Marc
Lokhov, Andrey Y.
author_facet Smedira, Devin
Jayakumar, Abhijith
Misra, Sidhant
Vuffray, Marc
Lokhov, Andrey Y.
contents Learning of continuous exponential family distributions with unbounded support remains an important area of research for both theory and applications in high-dimensional statistics. In recent years, score matching has become a widely used method for learning exponential families with continuous variables due to its computational ease when compared against maximum likelihood estimation. However, theoretical understanding of the statistical properties of score matching is still lacking. In this work, we provide a non-asymptotic sample complexity analysis for learning the structure of exponential families of polynomials with score matching. The derived sample bounds show a polynomial dependence on the model dimension. These bounds are the first of its kind, as all prior work has shown only asymptotic bounds on the sample complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14168
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Finite Sample Bounds for Learning with Score Matching
Smedira, Devin
Jayakumar, Abhijith
Misra, Sidhant
Vuffray, Marc
Lokhov, Andrey Y.
Machine Learning
Data Structures and Algorithms
Learning of continuous exponential family distributions with unbounded support remains an important area of research for both theory and applications in high-dimensional statistics. In recent years, score matching has become a widely used method for learning exponential families with continuous variables due to its computational ease when compared against maximum likelihood estimation. However, theoretical understanding of the statistical properties of score matching is still lacking. In this work, we provide a non-asymptotic sample complexity analysis for learning the structure of exponential families of polynomials with score matching. The derived sample bounds show a polynomial dependence on the model dimension. These bounds are the first of its kind, as all prior work has shown only asymptotic bounds on the sample complexity.
title Finite Sample Bounds for Learning with Score Matching
topic Machine Learning
Data Structures and Algorithms
url https://arxiv.org/abs/2605.14168