Optimal Algorithms and Lower Bounds for Testing Closeness of Structured Distributions

Optimal Algorithms and Lower Bounds for Testing Closeness of Structured Distributions
复制标题

用于测试结构化分布的接近度的最佳算法和下界

DOI:
10.1109/focs.2015.76
复制
发表时间:
2015
期刊:
2015 IEEE 56th Annual Symposium on Foundations of Computer Science
影响因子:
--
通讯作者:
Vladimir Nikishkin
Vladimir Nikishkin
中科院分区:
--
文献类型:
--
作者:
Ilias Diakonikolas;D. Kane;Vladimir Nikishkin

文献摘要

参考文献

被引文献

相似文献

我们提供了一种通用的统一方法,可用于L <sub> 1 </sub>的近距离测试。未知(可能是任意的)单变量分布在AK距离公制下:给定样品访问具有密度函数P,Q:I→R的分布的访问,我们想区分p = q和∥p -q∥<sub> ak </sub>≥∈,概率至少为2/3。紧密度测试问题是θ(Max {K <sup> 4/5 </sup>/∈<sup> 6/5 </sup>,K <sup> 1/2 </sup>/sap>/∈<sup> 2 <sup> 2 <sup> /sup>})。复杂性,用于广泛的结构化分布类别。
We give a general unified method that can be used for L<sub>1</sub> closeness testing of a wide range of univariate structured distribution families. More specifically, we design a sample optimal and computationally efficient algorithm for testing the equivalence of two unknown (potentially arbitrary) univariate distributions under the Ak-distance metric: Given sample access to distributions with density functions p, q : I → R, we want to distinguish between the cases that p = q and ∥p - q∥<sub>Ak</sub> ≥ ∈ with probability at least 2/3. We show that for any k ≥ 2, ∈ > 0, the optimal sample complexity of the Ak-closeness testing problem is Θ(max{k<sup>4/5</sup>/∈<sup>6/5</sup>, k<sup>1/2</sup>/∈<sup>2</sup>}). This is the first o(k) sample algorithm for this problem, and yields new, simple L1 closeness testers, in most cases with optimal sample complexity, for broad classes of structured distributions.
通过 Ränyi 散度近似和估计 s 凹面密度。
DOI: 10.1214/15-aos1408
发表时间: 2016
影响因子: 4.5
作者:
Han,Qiyang;Wellner,JonA
通讯作者: Wellner,JonA
DOI: 10.1214/09-ejs526
发表时间: 2009
影响因子: 1.1
作者:
Jankowski,HannaK;Wellner,JonA
通讯作者: Wellner,JonA
DOI: 10.1214/15-aos1394
发表时间: 2016
影响因子: 4.5
作者:
Doss CR;Wellner JA
通讯作者: Wellner JA
近线性时间内的样本最优密度估计
DOI: 10.48550/arxiv.1506.00671
发表时间: 2015
期刊: --
影响因子: --
作者:
Acharya J
通讯作者: Acharya J
DOI: 10.1214/08-aos609
发表时间: 2009-06-01
影响因子: 4.5
作者:
Balabdaoui F;Rufibach K;Wellner JA
通讯作者: Wellner JA