Robust Group Synchronization via Cycle-Edge Message Passing

Robust Group Synchronization via Cycle-Edge Message Passing
复制标题

通过循环边缘消息传递实现稳健的组同步

DOI:
10.1007/s10208-021-09532-w
复制
发表时间:
2021
影响因子:
3
通讯作者:
Shi, Yunpeng
Shi, Yunpeng
中科院分区:
数学1区
文献类型:
--
作者:
Lerman, Gilad;Shi, Yunpeng

文献摘要

参考文献

被引文献

相似文献

我们提出了一个解决组同步问题的通用框架,其中我们重点研究了对抗性或均匀破坏以及足够小的噪声的设置。具体地说,我们应用了一种新的消息传递过程,该过程使用循环一致性信息来估计组比率的破坏程度,从而解决了我们设置的同步问题。我们首先解释了为什么群周期一致性信息对于有效地解决群同步问题是必不可少的。然后,我们为所提出的消息传递过程在具有对抗性破坏的确定性环境下建立了精确恢复和线性收敛保证。只要每条边的损坏周期比率以合理的常数为界,这些保证就有效。我们还证明了所提出的方法对亚高斯噪声的稳定性。在一个常见的一致腐败模型下,我们进一步建立了高概率精确恢复。
We propose a general framework for solving the group synchronization problem, where we focus on the setting of adversarial or uniform corruption and sufficiently small noise. Specifically, we apply a novel message passing procedure that uses cycle consistency information in order to estimate the corruption levels of group ratios and consequently solve the synchronization problem in our setting. We first explain why the group cycle consistency information is essential for effectively solving group synchronization problems. We then establish exact recovery and linear convergence guarantees for the proposed message passing procedure under a deterministic setting with adversarial corruption. These guarantees hold as long as the ratio of corrupted cycles per edge is bounded by a reasonable constant. We also establish the stability of the proposed procedure to sub-Gaussian noise. We further establish exact recovery with high probability under a common uniform corruption model.
DOI: 10.1016/j.acha.2010.02.001
发表时间: 2011-01-30
影响因子: 2.5
作者:
Singer, A.
通讯作者: Singer, A.
高度损坏场景中摄像机位置的估计:一切都围绕该底座,没有形状问题
DOI: --
发表时间: 2018
期刊: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Yunpeng Shi;Gilad Lerman
通讯作者: Gilad Lerman
DOI: 10.1093/comnet/cnu050
发表时间: 2015-09-01
影响因子: 2.1
作者:
Cucuringu, Mihai
通讯作者: Cucuringu, Mihai
通过最小非平方偏差恢复精确的相机位置
DOI: 10.1137/17m115061x
发表时间: 2018
影响因子: 2.1
作者:
Lerman, Gilad;Shi, Yunpeng;Zhang, Teng
通讯作者: Zhang, Teng
DOI: --
发表时间: 2017-12
期刊: Advances in neural information processing systems
影响因子: --
作者:
Xiangru Huang;Zhenxiao Liang;C. Bajaj;Qi-Xing Huang
通讯作者: Xiangru Huang;Zhenxiao Liang;C. Bajaj;Qi-Xing Huang