A note on additive complements of the squares

TL;DR

This paper improves bounds on the representation function related to additive complements of squares and advances understanding of a problem posed by Ben Green, showing new asymptotic behavior of the sequence involved.

Contribution

It refines previous lower bounds on the sum of representation counts and makes progress on Green's problem by establishing a new limsup inequality.

Findings

Improved the lower bound of the sum of representation counts to N^{1/2}

Established a new asymptotic inequality related to the sequence w_n

Progressed on a problem posed by Ben Green regarding the sequence's growth

Abstract

Let $\mathcal{S}=\{1^2,2^2,3^2,...\}$ be the set of squares and $\mathcal{W}=\{w_n\}_{n=1}^{\infty} \subset \mathbb{N}$ be an additive complement of $\mathcal{S}$ so that $\mathcal{S} + \mathcal{W} \supset \{n \in \mathbb{N}: n \geq N_0\}$ for some $N_0$. Let $\mathcal{R}_{\mathcal{S},\mathcal{W}}(n) = \#\{(s,w):n=s+w, s\in \mathcal{S}, w\in \mathcal{W}\} $. In 2017, Chen-Fang \cite{C-F} studied the lower bound of $\sum_{n=1}^NR_{\mathcal{S},\mathcal{W}}(n)$. In this note, we improve Cheng-Fang's result and get that $$\sum_{n=1}^NR_{\mathcal{S},\mathcal{W}}(n)-N\gg N^{1/2}.$$ As an application, we make some progress on a problem of Ben Green problem by showing that $$\limsup_{n\rightarrow\infty}\frac{\frac{\pi^2}{16}n^2-w_n}{n}\ge \frac{\pi}{4}+\frac{0.193\pi^2}{8}.$$