arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.02728cs.LG
收藏

稀疏图中具有两两测量和边信息的推理

Inference in Sparse Graphs with Pairwise Measurements and Side Information

Cornell University(康奈尔大学);University of California, Berkeley(加州大学伯克利分校)

Dylan J. Foster, Daniel Reichman, Karthik Sridharan

摘要:

我们考虑的统计问题,恢复一个隐藏的“地面真相”的二进制标记的顶点的一个图形的低汉明误差从嘈杂的边缘和顶点测量。我们提出了新的算法和一个尖锐的有限样本分析这个问题上的树和稀疏图,如超网格和环格的扩展性能差。我们的方法推广并改进了Globerson等人的方法。(2015),他们引入了二维网格晶格的问题。对于树,我们提供了一个简单,高效的算法,推断地面真理与最佳汉明误差具有最佳的样本复杂性,并意味着恢复结果的所有连接图。这里,边信息的存在对于获得非平凡恢复率是至关重要的。然后,我们展示了如何适应这种算法的树分解的边缘子图的某些图形家庭,如格,导致可以有效地获得的最佳恢复出错率。我们分析的重点是1)使用树分解以及边缘测量来产生一小类可行的顶点标记,以及2)应用受统计学习理论影响的分析,表明我们可以使用顶点测量从该类中推断出地面真相。我们展示了我们的方法在几个例子,包括超网格,环格,和纽曼-瓦特模型的小世界图的权力。对于二维网格,我们的结果通过在恒定高度区域获得最佳恢复而优于Globerson等人(2015)。

英文摘要:

We consider the statistical problem of recovering a hidden "ground truth" binary labeling for the vertices of a graph up to low Hamming error from noisy edge and vertex measurements. We present new algorithms and a sharp finite-sample analysis for this problem on trees and sparse graphs with poor expansion properties such as hypergrids and ring lattices. Our method generalizes and improves over that of Globerson et al. (2015), who introduced the problem for two-dimensional grid lattices. For trees we provide a simple, efficient, algorithm that infers the ground truth with optimal Hamming error has optimal sample complexity and implies recovery results for all connected graphs. Here, the presence of side information is critical to obtain a non-trivial recovery rate. We then show how to adapt this algorithm to tree decompositions of edge-subgraphs of certain graph families such as lattices, resulting in optimal recovery error rates that can be obtained efficiently The thrust of our analysis is to 1) use the tree decomposition along with edge measurements to produce a small class of viable vertex labelings and 2) apply an analysis influenced by statistical learning theory to show that we can infer the ground truth from this class using vertex measurements. We show the power of our method in several examples including hypergrids, ring lattices, and the Newman-Watts model for small world graphs. For two-dimensional grids, our results improve over Globerson et al. (2015) by obtaining optimal recovery in the constant-height regime.

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。

↑