在骨架已知条件下学习有界度多树
Learning bounded-degree polytrees with known skeleton
AI总结:
本文研究骨架已知时的有界度多树学习,提出多项式时间与样本复杂度的 d-多树学习算法,并用信息论下界证明其维度与精度依赖近乎最优。
摘要:
我们为有界度多树(bounded-degree polytrees)的高效恰当学习建立了有限样本保证;多树是一类丰富的高维概率分布,也是 Bayesian networks(贝叶斯网络)的子类,而贝叶斯网络是一种被广泛研究的图模型。最近,Bhattachacharyya 等人(2021)获得了恢复树结构贝叶斯网络(即 1-多树)的有限样本保证。我们扩展了他们的结果:在底层无向图(骨架)已知时,提出一种高效算法,可在任意有界 d 下以多项式时间和多项式样本复杂度学习 d-多树。我们还给出一个信息论样本复杂度下界作为补充,表明算法对维度和目标准确度参数的依赖近乎紧。
英文摘要:
We establish finite-sample guarantees for efficient proper learning of bounded-degree polytrees, a rich class of high-dimensional probability distributions and a subclass of Bayesian networks, a widely-studied type of graphical model. Recently, Bhattacharyya et al. (2021) obtained finite-sample guarantees for recovering tree-structured Bayesian networks, i.e., 1-polytrees. We extend their results by providing an efficient algorithm which learns $d$-polytrees in polynomial time and sample complexity for any bounded $d$ when the underlying undirected graph (skeleton) is known. We complement our algorithm with an information-theoretic sample complexity lower bound, showing that the dependence on the dimension and target accuracy parameters are nearly tight.
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。