arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.22192math.STcs.CCcs.DSstat.TH
收藏

估计问题的稳定算法下界

Stable Algorithms Lower Bounds for Estimation

Yale University(耶鲁大学)

Xifan Yu, Ilias Zadik

AI总结:

本文研究了统计估计问题中稳定算法的下界,通过MMSE不稳定性条件揭示了稳定算法的失效,并展示了多项任务中低次多项式方法的局限性。

摘要:

在本文中,我们证明了对于所有统计估计问题,自然的MMSE不稳定性(不连续性)条件会导致稳定算法失效,这为估计任务提供了一种OGP版本。利用这一准则,我们建立了稳定算法与多项式时间算法之间的分离,针对三种MMSE不稳定的任务(i)种植最短路径,其中Dijkstra算法有效;(ii)随机奇偶码,其中高斯消元有效;(iii)高斯子集和,其中基于格的方法有效。对于所有三种情况,我们进一步证明所有低次多项式都是稳定的,从而分离了低次多项式方法,并提出了一种新的方法来界低次MMSE。特别是,我们的技术表明MMSE不稳定性是短路径和无噪声奇偶码和高斯子集和的共同特征。最后,我们强调本文的工作为长期存在的物理信念提供了严格的算法基础,即一阶相变——在本设置中转化为MMSE不稳定性——对高效算法类别的基本限制。

英文摘要:

In this work, we show that for all statistical estimation problems, a natural MMSE instability (discontinuity) condition implies the failure of stable algorithms, serving as a version of OGP for estimation tasks. Using this criterion, we establish separations between stable and polynomial-time algorithms for the following MMSE-unstable tasks (i) Planted Shortest Path, where Dijkstra's algorithm succeeds, (ii) random Parity Codes, where Gaussian elimination succeeds, and (iii) Gaussian Subset Sum, where lattice-based methods succeed. For all three, we further show that all low-degree polynomials are stable, yielding separations against low-degree methods and a new method to bound the low-degree MMSE. In particular, our technique highlights that MMSE instability is a common feature for Shortest Path and the noiseless Parity Codes and Gaussian subset sum. Last, we highlight that our work places rigorous algorithmic footing on the long-standing physics belief that first-order phase transitions--which in this setting translates to MMSE-instability impose fundamental limits on classes of efficient algorithms.

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。

↑