The Projected Power Method: An Efficient Algorithm for Joint Alignment from Pairwise Differences
The Projected Power Method: An Efficient Algorithm for Joint Alignment from Pairwise Differences
复制标题
DOI：
10.1002/cpa.21760
复制
发表时间：
2018-08-01
影响因子：
3
通讯作者：
Candes, Emmanuel J.
中科院分区：
文献类型：
--
作者：
Chen, Yuxin;Candes, Emmanuel J.
各种应用都涉及到基于一些成对噪声数据为对象集合分配离散标签值。由于问题的离散性和非凸性结构，计算最优分配（例如，最大似然分配）乍一看就变得棘手。本文通过对混凝土节理问题的研究，在高效计算方面取得了进展；也就是说，恢复n个离散变量xi的问题是{1，…， m}, 1
Various applications involve assigning discrete label values to a collection of objects based on some pairwise noisy data. Due to the discrete-and hence nonconvex-structure of the problem, computing the optimal assignment (e.g., maximum-likelihood assignment) becomes intractable at first sight. This paper makes progress towards efficient computation by focusing on a concrete joint alignment problem; that is, the problem of recovering n discrete variables xi is an element of {1, ..., m}, 1