A Note on Non-Negative $L_1$-Approximating Polynomials

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lee, Jane H., Mehrotra, Anay, Zampetakis, Manolis
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914545474207744
author Lee, Jane H.
Mehrotra, Anay
Zampetakis, Manolis
author_facet Lee, Jane H.
Mehrotra, Anay
Zampetakis, Manolis
contents $L_1$-Approximating polynomials, i.e., polynomials that approximate indicator functions in $L_1$-norm under certain distributions, are widely used in computational learning theory. We study the existence of \textit{non-negative} $L_1$-approximating polynomials with respect to Gaussian distributions. This is a stronger requirement than $L_1$-approximation but weaker than sandwiching polynomials (which themselves have many applications). These non-negative approximating polynomials have recently found uses in smoothed learning from positive-only examples. In this short note, we prove that every class of sets with Gaussian surface area (GSA) at most $Γ$ under the standard Gaussian admits degree-$k$ non-negative polynomials that $\eps$-approximate its indicator functions in $L_1$-norm, for $k=\tilde{O}(Γ^2/\varepsilon^2)$. Equivalently, finite GSA implies $L_1$-approximation with the stronger pointwise guarantee that the approximating polynomial has range contained in $[0,\infty)$. Up to a constant-factor, this matches the degree of the best currently known Gaussian $L_1$-approximation degree bound without the non-negativity constraint.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08072
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Note on Non-Negative $L_1$-Approximating Polynomials
Lee, Jane H.
Mehrotra, Anay
Zampetakis, Manolis
Machine Learning
Data Structures and Algorithms
Statistics Theory
$L_1$-Approximating polynomials, i.e., polynomials that approximate indicator functions in $L_1$-norm under certain distributions, are widely used in computational learning theory. We study the existence of \textit{non-negative} $L_1$-approximating polynomials with respect to Gaussian distributions. This is a stronger requirement than $L_1$-approximation but weaker than sandwiching polynomials (which themselves have many applications). These non-negative approximating polynomials have recently found uses in smoothed learning from positive-only examples. In this short note, we prove that every class of sets with Gaussian surface area (GSA) at most $Γ$ under the standard Gaussian admits degree-$k$ non-negative polynomials that $\eps$-approximate its indicator functions in $L_1$-norm, for $k=\tilde{O}(Γ^2/\varepsilon^2)$. Equivalently, finite GSA implies $L_1$-approximation with the stronger pointwise guarantee that the approximating polynomial has range contained in $[0,\infty)$. Up to a constant-factor, this matches the degree of the best currently known Gaussian $L_1$-approximation degree bound without the non-negativity constraint.
title A Note on Non-Negative $L_1$-Approximating Polynomials
topic Machine Learning
Data Structures and Algorithms
Statistics Theory
url https://arxiv.org/abs/2605.08072