arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.03571stat.MLcs.LG
收藏

静态几何图形模型选择

Stationary Geometric Graphical Model Selection

John A. Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学约翰·A·保尔森工程与应用科学学院);Department of Electrical and Computer Engineering, Duke University(杜克大学电气与计算机工程系)

Ilya Soloveychik, Vahid Tarokh

摘要:

研究了样本不足情形下高斯马尔可夫场中的模型选择问题。在许多实际重要的情况下,底层网络嵌入到欧几里得空间中。利用自然的几何结构,我们引入了几何图上的空间平稳分布的概念。这直接将平稳时间序列的概念推广到没有时间轴的多维环境。我们发现,空间平稳性的想法导致显着降低的样本复杂性的模型选择相比,具有相同水平的稀疏性的抽象图。对于几何图形的随机传播的顶点和边缘的有界长度,我们开发严格的信息理论界的样本复杂性,并表明,有限数量的独立样本是足够的一致恢复。最后,我们开发了一种有效的技术,能够可靠和一致地重建图形与有限数量的测量。

英文摘要:

We consider the problem of model selection in Gaussian Markov fields in the sample deficient scenario. In many practically important cases, the underlying networks are embedded into Euclidean spaces. Using the natural geometric structure, we introduce the notion of spatially stationary distributions over geometric graphs. This directly generalizes the notion of stationary time series to the multidimensional setting lacking time axis. We show that the idea of spatial stationarity leads to a dramatic decrease in the sample complexity of the model selection compared to abstract graphs with the same level of sparsity. For geometric graphs on randomly spread vertices and edges of bounded length, we develop tight information-theoretic bounds on sample complexity and show that a finite number of independent samples is sufficient for a consistent recovery. Finally, we develop an efficient technique capable of reliably and consistently reconstructing graphs with a bounded number of measurements.

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。

↑