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 2402.05385math.OC
收藏

零阶低秩Hessian估计:基于矩阵恢复的视角

Zeroth-order Low-rank Hessian Estimation via Matrix Recovery

Tianyu Wang, Zicheng Wang, Jiajia Yu

AI总结:

本文从矩阵恢复视角研究低秩Hessian的零阶估计,提出基于适当矩阵测量的估计方法,证明仅需O(nr²log²n)次有限差分即可高概率精确恢复,无需非相干性假设,大幅降低计算开销。

摘要:

零阶Hessian估计器旨在利用最少的有限差分计算,在任意给定点恢复目标函数的Hessian矩阵。本文从矩阵恢复的视角研究低秩Hessian的零阶估计问题。我们的挑战在于,传统的矩阵恢复技术不能直接适用于我们的场景。它们要么需要非相干性假设(或其变体),要么在我们的设置中需要不切实际的大量有限差分计算。为克服这些障碍,我们采用与适当矩阵测量相一致的零阶Hessian估计,并为这些估计器证明了新的恢复保证。具体而言,我们证明:对于秩为$r$的Hessian矩阵$H \in \mathbb{R}^{n \times n}$,$\mathcal{O}(nr^2 \log^2 n)$次适当的零阶有限差分计算即可高概率地精确恢复$H$。与现有方法相比,我们的方法能大幅减少有限差分计算次数,且不需要任何非相干性假设。

英文摘要:

A zeroth-order Hessian estimator aims to recover the Hessian matrix of an objective function at any given point, using minimal finite-difference computations. This paper studies zeroth-order Hessian estimation for low-rank Hessians, from a matrix recovery perspective. Our challenge lies in the fact that traditional matrix recovery techniques are not directly suitable for our scenario. They either demand incoherence assumptions (or its variants), or require an impractical number of finite-difference computations in our setting. To overcome these hurdles, we employ zeroth-order Hessian estimations aligned with proper matrix measurements, and prove new recovery guarantees for these estimators. More specifically, we prove that for a Hessian matrix $H \in \mathbb{R}^{n \times n}$ of rank $r$, $ \mathcal{O}(nr^2 \log^2 n ) $ proper zeroth-order finite-difference computations ensures a highly probable exact recovery of $H$. Compared to existing methods, our method can greatly reduce the number of finite-difference computations, and does not require any incoherence assumptions.

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。

↑