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
影响因子:
2.5
通讯作者:
Xiao, Ying
中科院分区:
文献类型:
--
作者:
Feldman, Vitaly;Grigorescu, Elena;Reyzin, Lev;Vempala, Santosh S.;Xiao, Ying
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.
登录
查看更多内容
影响因子:
1.6
作者:
Pearson, Karl
通讯作者:
Pearson, Karl
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
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