arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1407.0581stat.ML
收藏

马尔可夫网络中直接稀疏变化学习的支持一致性

Support Consistency of Direct Sparse-Change Learning in Markov Networks

Song Liu, Taiji Suzuki, Raissa Relator, Jun Sese, Masashi Sugiyama, Kenji Fukumizu

摘要:

研究了两个马尔可夫网络$P$和$Q$之间稀疏结构变化的学习问题。最近的一项工作提出了通过估计两个马尔可夫网络模型之间的比率来学习变化\emph{directly},而不是将两个马尔可夫网络分别拟合到两组数据并找出它们的差异。本文给出了\emph{successful change detection}关于样本容量$n_p, n_q$、数据维数$m$和变边数$d$的充分条件.当使用一个无界密度比模型,我们证明了真正的稀疏变化可以一致地确定为$n_p = Ω(d^2 \log \frac{m^2+m}{2})$和$n_q = Ω({n_p^2})$,与指数衰减的上限学习误差。当假设密度比模型的有界性时,这样的样本复杂度可以改进为$\min(n_p, n_q) = Ω(d^2 \log \frac{m^2+m}{2})$。我们的理论保证可以应用于广泛的离散/连续马尔可夫网络。

英文摘要:

We study the problem of learning sparse structure changes between two Markov networks $P$ and $Q$. Rather than fitting two Markov networks separately to two sets of data and figuring out their differences, a recent work proposed to learn changes \emph{directly} via estimating the ratio between two Markov network models. In this paper, we give sufficient conditions for \emph{successful change detection} with respect to the sample size $n_p, n_q$, the dimension of data $m$, and the number of changed edges $d$. When using an unbounded density ratio model we prove that the true sparse changes can be consistently identified for $n_p = Ω(d^2 \log \frac{m^2+m}{2})$ and $n_q = Ω({n_p^2})$, with an exponentially decaying upper-bound on learning error. Such sample complexity can be improved to $\min(n_p, n_q) = Ω(d^2 \log \frac{m^2+m}{2})$ when the boundedness of the density ratio model is assumed. Our theoretical guarantee can be applied to a wide range of discrete/continuous Markov networks.

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。

↑