arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1207.1394cs.AI
收藏

图模型中的近优非近视信息值

Near-optimal Nonmyopic Value of Information in Graphical Models

Carnegie Mellon University(卡内基梅隆大学)

Andreas Krause, Carlos E. Guestrin

摘要:

在现实世界的系统,如传感器网络,一个基本的问题是最有效地减少不确定性的观测值的选择。更具体地说,我们解决了长期存在的问题,在图形模型中选择最翔实的变量子集。我们提出了第一个有效的随机算法,提供了一个常数因子(1-1/e-ε)近似保证任何ε> 0具有高的置信度。该算法利用了次模函数的理论,结合样本复杂度的多项式界。我们还证明了,没有多项式时间算法可以提供一个常数因子近似优于(1 - 1/e),除非P = NP。最后,我们提供了广泛的证据,我们的方法在两个复杂的现实世界的数据集上的有效性。

英文摘要:

A fundamental issue in real-world systems, such as sensor networks, is the selection of observations which most effectively reduce uncertainty. More specifically, we address the long standing problem of nonmyopically selecting the most informative subset of variables in a graphical model. We present the first efficient randomized algorithm providing a constant factor (1-1/e-epsilon) approximation guarantee for any epsilon > 0 with high confidence. The algorithm leverages the theory of submodular functions, in combination with a polynomial bound on sample complexity. We furthermore prove that no polynomial time algorithm can provide a constant factor approximation better than (1 - 1/e) unless P = NP. Finally, we provide extensive evidence of the effectiveness of our method on two complex real-world datasets.

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。

↑