arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.06147quant-phcs.DScs.LG
收藏

非独立同分布假设检验:从经典到量子

Non-iid hypothesis testing: from classical to quantum

Università di Bologna(博洛尼亚大学);Inria(法国国家信息与自动化技术研究院);Télécom Paris - LTCI(巴黎电信学院 - LTCI);Institut Polytechnique de Paris(巴黎高等理工学院);Department of Mathematical Sciences, University of Copenhagen(哥本哈根大学数学科学系);University of Illinois Urbana–Champaign(伊利诺伊大学厄巴纳-香槟分校);Carnegie Mellon University(卡内基梅隆大学)

Giacomo De Palma, Marco Fanizza, Connor Mowry, Ryan O'Donnell

AI总结:

研究非iid假设检验,经典情形用每分布2样本近最优区分,量子情形仅需每态1拷贝即可匹配iid最优,揭示量子优势,并引入量子Efron-Stein工具。

摘要:

我们研究非独立同分布(non-iid)设置下的假设检验(又称状态认证)。近期工作(Garg等人,2023)考虑了经典情形:给定来自 $[d] = \{1, 2, \dots, d\}$ 上 $T$ 个未知概率分布 $p_1, \dots, p_T$ 的(独立)样本,希望接受/拒绝其平均值 $p_{\mathrm{avg}}$ 等于已知假设分布 $q$ 的假设。Garg等人证明,若从每个 $p_i$ 仅取 $c = 2$ 个样本,且 $T \gg \frac{\sqrt{d}}{ε^2} + \frac{1}{ε^4}$,则能以高概率(whp)区分 $p_{\mathrm{avg}} = q$ 与 $d_{\mathrm{TV}}(p_{\mathrm{avg}},q) > ε$。这几乎匹配经典iid设置的最优结果(即 $T \gg \frac{\sqrt{d}}{ε^2}$)。除了最优地改进该结果(并推广到具有更严格距离度量的容错检验),我们还研究了非相同量子态的类似假设检验问题。在此我们揭示了一个意外现象:对于任意 $d$ 维假设态 $σ$,给定每个态 $ρ_1, \dots, ρ_T$ 仅一份拷贝($c = 1$),只要 $T \gg d/ε^2$,就能区分 $ρ_{\mathrm{avg}} = σ$ 与 $D_{\mathrm{tr}}(ρ_{\mathrm{avg}},σ) > ε$。(同样,我们推广到具有更严格距离度量的容错检验。)这匹配iid情形的最优结果,令人惊讶,因为在经典情形下用 $c = 1$ 做到这一点已被证明不可能。我们还展示了类似现象发生在未知态之间同一性检验的非iid扩展中。我们引入的一个技术工具可能具有独立意义:量子设置下的Efron-Stein不等式,以及更一般的Efron-Stein分解。

英文摘要:

We study hypothesis testing (aka state certification) in the non-identically distributed setting. A recent work (Garg et al. 2023) considered the classical case, in which one is given (independent) samples from $T$ unknown probability distributions $p_1, \dots, p_T$ on $[d] = \{1, 2, \dots, d\}$, and one wishes to accept/reject the hypothesis that their average $p_{\mathrm{avg}}$ equals a known hypothesis distribution $q$. Garg et al. showed that if one has just $c = 2$ samples from each $p_i$, and provided $T \gg \frac{\sqrt{d}}{ε^2} + \frac{1}{ε^4}$, one can (whp) distinguish $p_{\mathrm{avg}} = q$ from $d_{\mathrm{TV}}(p_{\mathrm{avg}},q) > ε$. This nearly matches the optimal result for the classical iid setting (namely, $T \gg \frac{\sqrt{d}}{ε^2}$). Besides optimally improving this result (and generalizing to tolerant testing with more stringent distance measures), we study the analogous problem of hypothesis testing for non-identical quantum states. Here we uncover an unexpected phenomenon: for any $d$-dimensional hypothesis state $σ$, and given just a single copy ($c = 1$) of each state $ρ_1, \dots, ρ_T$, one can distinguish $ρ_{\mathrm{avg}} = σ$ from $D_{\mathrm{tr}}(ρ_{\mathrm{avg}},σ) > ε$ provided $T \gg d/ε^2$. (Again, we generalize to tolerant testing with more stringent distance measures.) This matches the optimal result for the iid case, which is surprising because doing this with $c = 1$ is provably impossible in the classical case. We also show that the analogous phenomenon happens for the non-iid extension of identity testing between unknown states. A technical tool we introduce may be of independent interest: an Efron-Stein inequality, and more generally an Efron-Stein decomposition, in the quantum setting.

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。

↑