arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv cs/0309015cs.LG
收藏

基于统计学习理论的稀疏数据贝叶斯网络可靠高效推理

Reliable and Efficient Inference of Bayesian Networks from Sparse Data by Statistical Learning Theory

Dominik Janzing, Daniel Herrmann

摘要:

为了学习随机变量之间的(统计)依赖关系,如果任何任意的联合概率分布都可能发生,则需要在观察到的随机变量的数量上具有指数级大的样本大小。我们考虑稀疏数据强烈表明概率可以由简单贝叶斯网络描述的情况,即,一个小度Δ的图。那么这个简单的定律也将以高置信度解释进一步的数据。这是通过计算VC维的这些概率措施,对应于简单的图形集上的界限。这允许选择网络的结构风险最小化,并给出了可靠性界的估计联合措施的错误,而没有(与以前的文件相比)任何先验假设的一组可能的联合措施。对于常数Δ,搜索入度为Δ的最优贝叶斯网络的复杂性仅随随机变量个数的增加而多项式增加,而与给定图相关的最优联合测度可以通过凸优化来求出.

英文摘要:

To learn (statistical) dependencies among random variables requires exponentially large sample size in the number of observed random variables if any arbitrary joint probability distribution can occur. We consider the case that sparse data strongly suggest that the probabilities can be described by a simple Bayesian network, i.e., by a graph with small in-degree Δ. Then this simple law will also explain further data with high confidence. This is shown by calculating bounds on the VC dimension of the set of those probability measures that correspond to simple graphs. This allows to select networks by structural risk minimization and gives reliability bounds on the error of the estimated joint measure without (in contrast to a previous paper) any prior assumptions on the set of possible joint measures. The complexity for searching the optimal Bayesian networks of in-degree Δincreases only polynomially in the number of random varibales for constant Δand the optimal joint measure associated with a given graph can be found by convex optimization.

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。

↑