发表机构
University of Toronto; Weizmann Institute of Science(多伦多大学; 魏茨曼科学研究所)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文给出简短直接证明,在最坏情况下,即使随机算法,求解条件数为κ的线性方程组到相对误差ε需Ω(κlog(1/ε))次矩阵向量乘法,并由此推导出优化强凸二次函数的经典下界。
AI 中文摘要
在本文中,我们提供了一个简短而直接的证明,表明在 $A$ 的条件数为 $\kappa$ 且维度不受限制的情况下,即使对于随机算法,在最坏情况下,将 $Ax=b$ 近似求解到相对误差 $\varepsilon$ 需要 $\Omega(\kappa\log(1/\varepsilon))$ 次矩阵-向量乘法。这实质上恢复了 Dereziński、Epperly 和 Meyer [2026] 针对该设置的下界,他们优雅且更通用的方法激励我们寻求一个简短直接的证明。一个直接的归约意味着优化强凸二次函数的经典 $\Omega(\sqrt{\kappa}\log(1/\varepsilon))$ 下界,该下界适用于随机算法。
英文摘要
In this note, we provide a short and direct proof that approximately solving $Ax=b$ to relative error $\varepsilon$, where $A$ has condition number $κ$ and unrestricted dimension, requires $Ω(κ\log(1/\varepsilon))$ matrix-vector multiplications in the worst case, even for randomized algorithms. This essentially recovers the lower bound of Dereziński, Epperly and Meyer [2026] for this setting, whose elegant and more general approach inspired us to seek a short direct proof. A straightforward reduction implies the classical $Ω(\sqrtκ\log(1/\varepsilon))$ lower bound for optimizing strongly convex quadratic functions, applicable to randomized algorithms.
Comments9 pages