arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.06783math.APcs.LGcs.NAmath.NAmath.PR
收藏

泊松学习收敛到带测度数据的泊松方程的收敛速率

Convergence rates for Poisson learning to a Poisson equation with measure data

Center for Artificial Intelligence and Data Science (CAIDAS), University of Würzburg(维尔茨堡大学人工智能与数据科学中心);School of Mathematics, University of Minnesota(明尼苏达大学数学学院);Hausdorff Center for Mathematics, University of Bonn(波恩大学豪斯多夫数学中心)

Leon Bungert, Jeff Calder, Max Mihailescu, Kodjo Houssou, Amber Yuan

AI总结:

本文针对带测度数据的泊松方程对应的图半监督算法Poisson Learning,通过误差估计、变分技术与热核正则化结合的方法,证明了其离散到连续的$L^1$收敛速率及高概率成立条件。

摘要:

本文证明了Poisson Learning(泊松学习)的离散到连续收敛速率,这是一种基于图的半监督学习算法,其核心是求解图泊松方程,该方程的源项由位于标记点、携带标签信息的狄拉克δ函数的线性组合构成。对应的连续方程是欧几里得域$\Omega\subset \mathbb{R}^d$中带测度数据的泊松方程。这类方程的奇异性带来了挑战,需要采用包含多个不同部分的方法:(1) 我们证明了当泊松方程的测度数据与支撑在球上的(近似)径向函数卷积时的定量误差估计。(2) 我们利用定量变分技术,在带宽为$\varepsilon>0$的随机几何图上,针对有界源项证明了离散到连续的收敛速率。(3) 我们展示了如何通过图热核的软化来正则化图泊松方程,并研究了随机几何图上热核的精细渐近性质。结合这三个核心部分,我们得到了$L^1$收敛速率:对于一般数据分布,速率在忽略对数因子的情况下为$O(\varepsilon^{\frac{1}{d+2}})$;对于均匀分布的数据,速率为$O(\varepsilon^{\frac{2-\sigma}{d+4}})$,其中$\sigma>0$。当$\varepsilon\gg\left({\log n}/{n}\right)^q$时,这些速率以高概率成立,其中$n$表示图的顶点数,$q \approx \frac{1}{3d}$。

英文摘要:

In this paper we prove discrete to continuum convergence rates for Poisson Learning, a graph-based semi-supervised learning algorithm that is based on solving the graph Poisson equation with a source term consisting of a linear combination of Dirac deltas located at labeled points and carrying label information. The corresponding continuum equation is a Poisson equation with measure data in a Euclidean domain $Ω\subset \mathbb{R}^d$. The singular nature of these equations is challenging and requires an approach with several distinct parts: (1) We prove quantitative error estimates when convolving the measure data of a Poisson equation with (approximately) radial function supported on balls. (2) We use quantitative variational techniques to prove discrete to continuum convergence rates on random geometric graphs with bandwidth $\varepsilon>0$ for bounded source terms. (3) We show how to regularize the graph Poisson equation via mollification with the graph heat kernel, and we study fine asymptotics of the heat kernel on random geometric graphs. Combining these three pillars we obtain $L^1$ convergence rates that scale, up to logarithmic factors, like $O(\varepsilon^{\frac{1}{d+2}})$ for general data distributions, and $O(\varepsilon^{\frac{2-σ}{d+4}})$ for uniformly distributed data, where $σ>0$. These rates are valid with high probability if $\varepsilon\gg\left({\log n}/{n}\right)^q$ where $n$ denotes the number of vertices of the graph and $q \approx \frac{1}{3d}$.

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。

↑