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 2406.14211math.OCcs.NAmath.NA
收藏

通过去奇异化对有界秩矩阵进行优化可实现联合全局和局部保证

Optimization over bounded-rank matrices through a desingularization enables joint global and local guarantees

Ecole Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院)

Quentin Rebjock, Nicolas Boumal

AI总结:

研究对有界秩矩阵优化的收敛保证问题,基于Khrulkov和Oseledets的去奇异化思想,开发黎曼几何,使算法能全局收敛到驻点且局部收敛快,在矩阵补全任务中与其他方法效果相当。

摘要:

对有界秩矩阵进行优化的收敛保证难以获得,因为可行集是非光滑且非凸的代数簇。现有技术包括对有界秩矩阵直接优化、固定秩优化和LR参数化,都缺乏全局保证或快速局部收敛性。我们研究一种提升几何结构使算法兼具两者。Khrulkov和Oseledets通过去奇异化对有界秩簇进行参数化。在此基础上,我们为去奇异化开发黎曼几何并考虑数值因素,确保许多标准算法能全局收敛到驻点且局部收敛快。在矩阵补全任务中,该方法与其他方法相当。

英文摘要:

Convergence guarantees for optimization over bounded-rank matrices are delicate to obtain because the feasible set is a nonsmooth and nonconvex algebraic variety. Existing techniques include direct optimization over bounded-rank matrices (e.g., projected gradient descent), fixed-rank optimization (over the maximal-rank stratum), and the LR parameterization. They all lack either global guarantees (the ability to accumulate only at stationary points) or fast local convergence (e.g., if the limit has non-maximal rank). We study a lifted geometry that allows algorithms to enjoy both. Khrulkov and Oseledets [2018] parameterize the bounded-rank variety via a desingularization to recast the optimization problem onto a smooth manifold. Building on their ideas, we develop a Riemannian geometry for this desingularization, also with care for numerical considerations. We use it to ensure conditions that, for many standard algorithms, yield global convergence to stationary points with fast local rates. On matrix completion tasks, we find that this approach is comparable to others.

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。

↑