Statistical Algorithms and a Lower Bound for Detecting Planted Cliques

Statistical Algorithms and a Lower Bound for Detecting Planted Cliques
复制标题

检测植入派系的统计算法和下界

DOI:
10.1145/3046674
复制
发表时间:
2017
期刊:
影响因子:
2.5
通讯作者:
Xiao, Ying
Xiao, Ying
中科院分区:
计算机科学2区
文献类型:
--
作者:
Feldman, Vitaly;Grigorescu, Elena;Reyzin, Lev;Vempala, Santosh S.;Xiao, Ying

文献摘要

参考文献

被引文献

相似文献

我们引入了一个框架,用于证明分布上计算问题的下界,而算法可以通过访问统计查询来实现。对于这样的算法,对输入分布的访问仅限于从输入分布中随机抽取的样本中获得任何给定函数的期望的估计,而不是直接访问样本。大多数在理论和实践中感兴趣的自然算法,例如基于矩的方法,局部搜索,凸优化的标准迭代方法,MCMC和模拟退火,都可以在这个框架中实现。我们的框架基于并推广了学习理论中的统计查询模型[Kearns 1998]。我们的主要应用是对于任意常数δ > 0,当种植团的大小为o (n1/2−δ)时,用于检测种植二部团分布(或种植密集子图分布)的任何统计查询算法的复杂度的近最优下界。这些问题变体的假定硬度已被用来证明其他几个问题的硬度,并作为密码学应用中安全性的保证。我们的下限提供了硬度的具体证据,从而支持了这些假设。
We introduce a framework for proving lower bounds on computational problems over distributions against algorithms that can be implemented using access to astatistical queryoracle. For such algorithms, access to the input distribution is limited to obtaining an estimate of the expectation of any given function on a sample drawn randomly from the input distribution rather than directly accessing samples. Most natural algorithms of interest in theory and in practice, for example, moments-based methods, local search, standard iterative methods for convex optimization, MCMC, and simulated annealing, can be implemented in this framework. Our framework is based on, and generalizes, the statistical query model in learning theory [Kearns 1998].Our main application is a nearly optimal lower bound on the complexity ofanystatistical query algorithm for detecting planted bipartite clique distributions (or planted dense subgraph distributions) when the planted clique has sizeO(n1/2 − δ) for any constant δ > 0. The assumed hardness of variants of these problems has been used to prove hardness of several other problems and as a guarantee for security in cryptographic applications. Our lower bounds provide concrete evidence of hardness, thus supporting these assumptions.
圆锥系统的高效重缩放感知器算法
DOI: 10.2139/ssrn.937948
发表时间: 2006
期刊: Econometrics eJournal
影响因子: --
作者:
A. Belloni;R. Freund;S. Vempala
通讯作者: S. Vempala
DOI: --
发表时间: 2022
期刊:
影响因子: --
作者:
Tsuchikawa T.;Kaneda H.;Oyabu S.;Kokusho T.;Kobayashi H.;Yamagishi M.;Toba Y.;Kiyoto Yoshino
通讯作者: Kiyoto Yoshino
DOI: 10.1137/090766991
发表时间: 2009-01
期刊: --
影响因子: --
作者:
Elad Hazan;Robert Krauthgamer
通讯作者: Elad Hazan;Robert Krauthgamer
极小极大子矩阵检测中的计算障碍
DOI: 10.1214/14-aos1300
发表时间: 2013
期刊: ArXiv
影响因子: --
作者:
Zongming Ma;Yihong Wu
通讯作者: Yihong Wu