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 2305.15136math.OCcs.LG
收藏

ReSync:基于黎曼次梯度的鲁棒旋转同步

ReSync: Riemannian Subgradient-based Robust Rotation Synchronization

Shanghai University of Finance and Economics(上海财经大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));The Chinese University of Hong Kong(香港中文大学)

Huikang Liu, Xiao Li, Anthony Man-Cho So

AI总结:

本文提出基于黎曼次梯度的 ReSync 算法,通过旋转群上的最小非平方模型直接恢复旋转,并证明其在随机损坏下可线性收敛至真实旋转。

摘要:

本工作提出了 ReSync,这是一种基于黎曼次梯度的算法,用于求解在众多工程应用中出现的鲁棒旋转同步问题。ReSync 在旋转群上求解最小非平方极小化模型,该模型是非光滑且非凸的,旨在直接恢复潜在旋转。我们在随机损坏情形下为 ReSync 提供了强有力的理论保证。具体而言,我们首先证明 ReSync 的初始化过程能够产生一个合适的初始点,该点位于真实旋转周围的局部区域内。接着,我们建立上述模型的弱尖锐性,并利用该性质推导出 ReSync 向真实旋转的局部线性收敛性。综合这些保证,我们得出结论:在适当条件下,ReSync 会线性收敛到真实旋转。实验结果证明了 ReSync 的有效性。

英文摘要:

This work presents ReSync, a Riemannian subgradient-based algorithm for solving the robust rotation synchronization problem, which arises in various engineering applications. ReSync solves a least-unsquared minimization formulation over the rotation group, which is nonsmooth and nonconvex, and aims at recovering the underlying rotations directly. We provide strong theoretical guarantees for ReSync under the random corruption setting. Specifically, we first show that the initialization procedure of ReSync yields a proper initial point that lies in a local region around the ground-truth rotations. We next establish the weak sharpness property of the aforementioned formulation and then utilize this property to derive the local linear convergence of ReSync to the ground-truth rotations. By combining these guarantees, we conclude that ReSync converges linearly to the ground-truth rotations under appropriate conditions. Experiment results demonstrate the effectiveness of ReSync.

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。

↑