点云上全变差的连续极限
Continuum limit of total variation on point clouds
摘要:
我们认为点云作为欧几里得整环上的测度的随机样本获得。表示点云的图是通过基于它们连接的点之间的距离向边分配权重来获得的。我们的目标是开发研究一致性所需的数学工具,随着可用数据点数量的增加,基于图的机器学习算法用于聚类等任务。特别是,我们研究什么时候是切割能力,更一般地说,全变差,在这些图上的周长(全变差)在连续设置的一个很好的近似。我们在$Γ$ -收敛的设置中解决这个问题。我们得到几乎最优的条件上的缩放,随着点的数量的增加,在其上的点由边缘连接的邻域的大小的$Γ$ -收敛举行。通过基于运输的度量来实现限制,该度量允许适当地比较在不同点云上定义的泛函。
英文摘要:
We consider point clouds obtained as random samples of a measure on a Euclidean domain. A graph representing the point cloud is obtained by assigning weights to edges based on the distance between the points they connect. Our goal is to develop mathematical tools needed to study the consistency, as the number of available data points increases, of graph-based machine learning algorithms for tasks such as clustering. In particular, we study when is the cut capacity, and more generally total variation, on these graphs a good approximation of the perimeter (total variation) in the continuum setting. We address this question in the setting of $Γ$-convergence. We obtain almost optimal conditions on the scaling, as number of points increases, of the size of the neighborhood over which the points are connected by an edge for the $Γ$-convergence to hold. Taking the limit is enabled by a transportation based metric which allows to suitably compare functionals defined on different point clouds.
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。