arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1708.02728cs.DScs.ITcs.LGmath.ITmath.STstat.TH
收藏

高概率最优身份检验

Optimal Identity Testing with High Probability

USC(南加利福尼亚大学);MIT(麻省理工学院);UT Austin(得克萨斯大学奥斯汀分校)

Ilias Diakonikolas, Themis Gouleakis, John Peebles, Eric Price

摘要:

我们研究的问题,测试身份对一个给定的分布集中在高置信度制度。更确切地说,给定来自$n$元素上的未知分布$p$、明确给定的分布$q$和参数$0< ε, δ< 1$的样本,我们希望区分{概率至少为$1-δ$的\em},分布是否与$\varepsilon$相同-在总变化距离上。大多数先前的工作集中在$δ= Ω(1)$的情况下,对于该情况,已知同一性测试的样本复杂度为$Θ(\sqrt{n}/ε^2)$。给定这样的算法,可以通过黑盒放大获得任意小的$δ$值,黑盒放大将所需的样本数乘以$Θ(\log(1/δ))$。我们表明,黑盒放大是次优的任何$δ= o(1)$,并给出了一个新的身份测试,实现了最佳的样本复杂性。我们的新的上限和下限表明,最佳的样本复杂性的身份测试是\[ Θ\left( \frac{1}{ε^2}\left(\sqrt{n \log(1/δ)} + \log(1/δ) \right)\right) \]的任何$n, \varepsilon$,和$δ$。对于均匀性测试的特殊情况,其中给定的分布是域上的均匀分布$U_n$,我们的新测试器令人惊讶地简单:要测试$p = U_n$与$d_{\mathrm TV}(p, U_n) \geq \varepsilon$是否一致,我们只需阈值$d_{\mathrm TV}(\widehat{p}, U_n)$,其中$\widehat{p}$是经验概率分布。这个简单的“插件”估计器是样本最优的事实是令人惊讶的,即使在恒定的$δ$情况下。事实上,人们认为,即使对于$\varepsilon$和$δ$的恒定值,这种测试仪也不会达到次线性样品复杂性。

英文摘要:

We study the problem of testing identity against a given distribution with a focus on the high confidence regime. More precisely, given samples from an unknown distribution $p$ over $n$ elements, an explicitly given distribution $q$, and parameters $0< ε, δ< 1$, we wish to distinguish, {\em with probability at least $1-δ$}, whether the distributions are identical versus $\varepsilon$-far in total variation distance. Most prior work focused on the case that $δ= Ω(1)$, for which the sample complexity of identity testing is known to be $Θ(\sqrt{n}/ε^2)$. Given such an algorithm, one can achieve arbitrarily small values of $δ$ via black-box amplification, which multiplies the required number of samples by $Θ(\log(1/δ))$. We show that black-box amplification is suboptimal for any $δ= o(1)$, and give a new identity tester that achieves the optimal sample complexity. Our new upper and lower bounds show that the optimal sample complexity of identity testing is \[ Θ\left( \frac{1}{ε^2}\left(\sqrt{n \log(1/δ)} + \log(1/δ) \right)\right) \] for any $n, \varepsilon$, and $δ$. For the special case of uniformity testing, where the given distribution is the uniform distribution $U_n$ over the domain, our new tester is surprisingly simple: to test whether $p = U_n$ versus $d_{\mathrm TV}(p, U_n) \geq \varepsilon$, we simply threshold $d_{\mathrm TV}(\widehat{p}, U_n)$, where $\widehat{p}$ is the empirical probability distribution. The fact that this simple "plug-in" estimator is sample-optimal is surprising, even in the constant $δ$ case. Indeed, it was believed that such a tester would not attain sublinear sample complexity even for constant values of $\varepsilon$ and $δ$.

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。

↑