Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The link between $1$-norm approximation and effective Positivstellensatze for the hypercube (2404.04190v2)

Published 5 Apr 2024 in math.OC

Abstract: The Schm\"udgen's Positivstellensatz gives a certificate to verify positivity of a strictly positive polynomial $f$ on a compact, basic, semi-algebraic set $\mathbf{K} \subset \mathbb{R}n$. A Positivstellensatz of this type is called effective if one may bound the degrees of the polynomials appearing in the certificate in terms of properties of $f$. If $\mathbf{K} = [-1,1]n$ and $0 < f_\min := \min_{x \in \mathbf{K}} f(x)$, then the degrees of the polynomials appearing in the certificate may be bounded by $O\left(\sqrt{\frac{f_\max - f_\min}{f_\min}}\right)$, where $f_\max := \max_{x \in \mathbf{K}} f(x)$, as was recently shown by Laurent and Slot [Optimization Letters 17:515-530, 2023]. The big-O notation suppresses dependence on $n$ and the degree $d$ of $f$. In this paper we show a similar result, but with a better dependence on $n$ and $d$. In particular, our bounds depend on the $1$-norm of the coefficients of $f$, that may readily be calculated.

Summary

We haven't generated a summary for this paper yet.