arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.03772cs.LGcs.NAmath.APmath.NAstat.ML
收藏

图的Lipschitz学习的连续极限

Continuum Limit of Lipschitz Learning on Graphs

University of Erlangen–Nürnberg(埃尔朗根-纽伦堡大学);University of Bonn(波恩大学)

Tim Roith, Leon Bungert

摘要:

近年来,用基于图的方法来解决半监督学习问题已经成为一种趋势,因为图可以表示各种数据并为研究连续极限提供合适的框架,例如,微分算子这里流行的策略是$p$ -Laplacian学习,它对未标记数据集上所寻求的推理函数提出了平滑条件。对于$p<\infty$连续极限的这种方法进行了研究,使用工具从$Γ$收敛。对于被称为Lipschitz学习的$p=\infty$情形,利用粘性解的概念研究了相关无穷拉普拉斯方程的连续极限。在这项工作中,我们证明了连续极限Lipschitz学习使用$Γ$收敛。特别是,我们定义了一个序列的泛函近似的最大的局部Lipschitz常数的一个图函数和证明$Γ$ -收敛的$L^\infty$ -拓扑的上确界范数的梯度图变得更加密集。此外,我们证明了紧的泛函,这意味着收敛的极小。在我们的分析中,我们允许一组不同的标签数据,收敛到一个一般的封闭的Hausdorff距离。我们将我们的结果应用到非线性基态,即,最小的约束$L^p$ -范数,并作为一个副产品,证明收敛的图距离函数的测地距离函数。

英文摘要:

Tackling semi-supervised learning problems with graph-based methods has become a trend in recent years since graphs can represent all kinds of data and provide a suitable framework for studying continuum limits, e.g., of differential operators. A popular strategy here is $p$-Laplacian learning, which poses a smoothness condition on the sought inference function on the set of unlabeled data. For $p<\infty$ continuum limits of this approach were studied using tools from $Γ$-convergence. For the case $p=\infty$, which is referred to as Lipschitz learning, continuum limits of the related infinity-Laplacian equation were studied using the concept of viscosity solutions. In this work, we prove continuum limits of Lipschitz learning using $Γ$-convergence. In particular, we define a sequence of functionals which approximate the largest local Lipschitz constant of a graph function and prove $Γ$-convergence in the $L^\infty$-topology to the supremum norm of the gradient as the graph becomes denser. Furthermore, we show compactness of the functionals which implies convergence of minimizers. In our analysis we allow a varying set of labeled data which converges to a general closed set in the Hausdorff distance. We apply our results to nonlinear ground states, i.e., minimizers with constrained $L^p$-norm, and, as a by-product, prove convergence of graph distance functions to geodesic distance functions.

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。

↑