arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1212.0171cs.ITcs.LGmath.ITstat.ML
收藏

二次极小化问题的消息传递算法

Message-Passing Algorithms for Quadratic Minimization

École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Yale University(耶鲁大学)

Nicholas Ruozzi, Sekhar Tatikonda

摘要:

高斯置信传播(GaBP)是一种迭代算法,用于计算多元高斯分布的平均值,或者等价地,计算多元正定二次函数的最小值。保证GaBP的收敛性和正确性的充分条件,如可行走求和性,是已知的,但GaBP可能无法收敛到正确的解决方案,给定一个任意的正定二次函数。正如在以前的工作中所观察到的,GaBP算法无法收敛,如果算法产生的计算树不是正定的。在这项工作中,我们将证明GaBP算法的故障模式可以通过图覆盖来理解,并且我们证明了最小和算法的参数化推广可以用于确保计算树在输入矩阵正定时保持正定。我们证明,所得到的算法是密切相关的其他迭代计划,如二次最小化的高斯-赛德尔和雅可比算法。最后,根据经验,我们观察到,总是存在一个参数的选择,使得GaBP算法的上述推广收敛。

英文摘要:

Gaussian belief propagation (GaBP) is an iterative algorithm for computing the mean of a multivariate Gaussian distribution, or equivalently, the minimum of a multivariate positive definite quadratic function. Sufficient conditions, such as walk-summability, that guarantee the convergence and correctness of GaBP are known, but GaBP may fail to converge to the correct solution given an arbitrary positive definite quadratic function. As was observed in previous work, the GaBP algorithm fails to converge if the computation trees produced by the algorithm are not positive definite. In this work, we will show that the failure modes of the GaBP algorithm can be understood via graph covers, and we prove that a parameterized generalization of the min-sum algorithm can be used to ensure that the computation trees remain positive definite whenever the input matrix is positive definite. We demonstrate that the resulting algorithm is closely related to other iterative schemes for quadratic minimization such as the Gauss-Seidel and Jacobi algorithms. Finally, we observe, empirically, that there always exists a choice of parameters such that the above generalization of the GaBP algorithm converges.

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。

↑