arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.04060math.NAcs.LGcs.NA
收藏

浅层ReLU$^k$网络在球面上逼近的配置相关下界

Configuration-Dependent Lower Bounds for Approximation by Shallow ReLU$^k$ Networks on the Sphere

King Abdullah University of Science and Technology(国王阿卜杜勒-阿齐兹大学)

Tong Mao, Jinchao Xu

AI总结:

本文为球面上浅层ReLU$^k$网络逼近建立配置相关下界,揭示其饱和阶,表明线性化神经网络逼近受经典饱和框架限制,优势有限。

摘要:

我们在单位球面$\SS^d$上为浅层ReLU$^k$神经网络建立了两个相关但在逻辑上不同的结果。首先,对于任意一组内部神经网络参数,固定目标函数(光滑度$r>\tfrac{d+2k+1}{2}$)的最佳$\mathcal{L}^2(\SS^d)$逼近具有渐近下界,该下界由$n^{-1/2}\underline{h}^{k+1/2}$的常数倍给出,其中$\underline{h}$表示归一化内部参数集的反对称分离距离。该下界通过$\underline{h}$显式依赖于参数配置,且无需对参数施加额外假设。其次,对于反对称拟均匀参数,$\underline{h}\simeq n^{-1/d}$,该下界为此类参数族确立了精确的饱和阶$n^{-\frac{d+2k+1}{2d}}$:正则性大于$\frac{d+2k+1}{2}$且满足所需奇偶条件的目标函数可以以此速率逼近,而任何严格更快的逼近速率都将迫使目标函数为零。因此,我们的结果将线性化神经网络逼近置于经典饱和框架内,并表明尽管ReLU$^k$网络空间可以优于同阶有限元,但这种优势本质上受到限制。

英文摘要:

We establish two related but logically distinct results for shallow ReLU$^k$ neural networks on the unit sphere $\SS^d$. First, for an arbitrary set of inner neural-network parameters, the best $\mathcal{L}^2(\SS^d)$ approximation of a fixed target function with smoothness $r>\tfrac{d+2k+1}{2}$ admits an asymptotic lower bound given by a constant multiple of $n^{-1/2}\underline{h}^{k+1/2}$, where $\underline{h}$ denotes the antipodal separation distance of the normalized inner-parameter set. This lower bound depends explicitly on the parameter configuration through $\underline{h}$ and applies without additional assumptions on the parameters. Second, for antipodally quasi-uniform parameters, $\underline{h}\simeq n^{-1/d}$, and the lower bound establishes the exact saturation order $n^{-\frac{d+2k+1}{2d}}$ for such parameter families: a target function with regularity greater than $\frac{d+2k+1}{2}$ and satisfying the required parity condition can be approximated at this rate, whereas approximation at any strictly faster rate forces the target function to be zero. Our results therefore place linearized neural-network approximation within the classical saturation framework and show that, although ReLU$^k$ network spaces can outperform finite elements of the same degree, this advantage is intrinsically limited.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑