arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2607.07540quant-phcs.ITmath.ITmath.STstat.TH
收藏

基于量子论证的高阶泛函极小极大估计

Towards Minimax Estimation of High-Order Functionals by Quantum Arguments

School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机学院)

Qisheng Wang

AI总结:

该研究从量子计算角度出发,提出新方法用于高阶泛函极小极大估计。给出针对经典与量子泛函的估计器,在特定范围内达到最优L_2速率与样本复杂度,改进先前上界,且估计器用统一框架和量子原语构建,运行于量子计算机,揭示新路径。

摘要:

我们从量子计算的角度提出了一种用于高阶泛函极小极大估计的新方法。具体而言,对于任意实数α≫1,我们给出了两个估计器,一个用于离散分布P的经典泛函F_α(P)=∑_i^S p_i^α,另一个用于混合态ρ的量子泛函F_α(ρ)=tr(ρ^α)。这些泛函与Rényi熵和Tsallis熵密切相关。我们表明,在α≲n≲α^(3 - o(1))范围内,两个估计器都能达到极小极大最优L_2速率αn^(-1),其中P的支持大小S或ρ的维度可能远大于样本数量n。结果,两个估计器都实现了最优样本复杂度n≍α,改进了Jiao等人(2017年IEEE信息论学报)对经典泛函和Chen与Wang(2025年COLT)对量子泛函建立的先前最佳上界O(α^2)。我们的估计器在一个统一框架下使用量子原语构建,并在量子计算机上以线性时间运行。这项工作揭示了从量子计算到统计学的一条意外路径,为泛函估计提出了一种概念上新的方法。它增加了经典定理的量子证明的不断增长的列表。

英文摘要:

We propose a novel approach to the minimax estimation of high-order functionals from the perspective of quantum computing. Specifically, for any real number $α\gg 1$, we present two estimators, one for the classical functional $\mathrm{F}_α(P) = \sum_{i=1}^S p_i^α$ of a discrete distribution $P$ and the other for the quantum functional $\mathrm{F}_α(ρ) = \operatorname{tr}(ρ^α)$ of a mixed state $ρ$. These functionals have close connections with the Rényi entropy and the Tsallis entropy. We show that both estimators achieve the minimax optimal $L_2$ rate $α\mathsf{n}^{-1}$ in the range $α\lesssim \mathsf{n} \lesssim α^{3-o(1)}$, where the support size $S$ of $P$ or the dimension of $ρ$ can be much larger than the number of samples $\mathsf{n}$. As a result, both estimators achieve the \textit{optimal} sample complexity $\mathsf{n} \asymp α$, improving upon the prior best upper bounds $O(α^2)$ established by Jiao, Venkat, Han, and Weissman (IEEE Trans. Inf. Theory 2017) for classical functionals and Chen and Wang (COLT 2025) for quantum functionals. Our estimators are constructed under a unified framework using quantum primitives and run in linear time on a quantum computer. This work reveals an unexpected path from quantum computing to statistics, suggesting a conceptually new methodology for functional estimation. It adds to the growing list of quantum proofs for classical theorems.

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。

↑