Optimal testing of discrete distributions with high probability
Optimal testing of discrete distributions with high probability
复制标题
高概率离散分布的最优测试
DOI:
10.1145/3406325.3450997
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Price, Eric
中科院分区:
文献类型:
--
作者:
Diakonikolas, Ilias;Gouleakis, Themis;Kane, Daniel M.;Peebles, John;Price, Eric
We study the problem of testing discrete distributions with a focus on the high probability regime. Specifically, given samples from one or more discrete distributions, a propertyP, and parameters 0< є, δ <1, we want to distinguishwith probability at least1−δ whether these distributions satisfyPor are є-far fromPin total variation distance. Most prior work in distribution testing studied the constant confidence case (corresponding to δ = Ω(1)), and provided sample-optimal testers for a range of properties. While one can always boost the confidence probability of any such tester by black-box amplification, this generic boosting method typically leads to sub-optimal sample bounds.Here we study the following broad question: For a given propertyP, can wecharacterizethe sample complexity of testingPas a function of all relevant problem parameters, including the error probability δ? Prior to this work, uniformity testing was the only statistical task whose sample complexity had been characterized in this setting. As our main results, we provide the first algorithms for closeness and independence testing that are sample-optimal, within constant factors, as a function of all relevant parameters. We also show matching information-theoretic lower bounds on the sample complexity of these problems. Our techniques naturally extend to give optimal testers for related problems. To illustrate the generality of our methods, we give optimal algorithms for testing collections of distributions and testing closeness with unequal sized samples.
登录
查看更多内容
DOI:
--
发表时间:
2018
期刊:
and Automata
影响因子:
--
作者:
Diakonikolas, Ilias;Gouleakis, Themis;Peebles, John;Price, Eric
通讯作者:
Price, Eric
影响因子:
2.5
作者:
C. Canonne;Ilias Diakonikolas;D. Kane;Alistair Stewart
通讯作者:
Alistair Stewart
DOI:
--
发表时间:
2016
期刊:
Annual Conference Computational Learning Theory
影响因子:
--
作者:
C. Daskalakis;Qinxuan Pan
通讯作者:
Qinxuan Pan
DOI:
10.1109/focs.2015.76
发表时间:
2015
期刊:
2015 IEEE 56th Annual Symposium on Foundations of Computer Science
影响因子:
--
作者:
Ilias Diakonikolas;D. Kane;Vladimir Nikishkin
通讯作者:
Vladimir Nikishkin
DOI:
--
发表时间:
2018
期刊:
Annual Conference Computational Learning Theory
影响因子:
--
作者:
Ilias Diakonikolas;D. Kane;John Peebles
通讯作者:
John Peebles