Skip to main content
QUICK REVIEW

[论文解读] Lower Bounds for Learning Quantum States with Single-Copy Measurements

Angus Lowe, Ashwin Nayak|arXiv (Cornell University)|Jul 29, 2022
Machine Learning and Algorithms被引用 6
一句话总结

该论文为使用单拷贝、非自适应或自适应测量学习量子态的样本复杂度建立了紧致的下界。证明了泡利层析(Pauli tomography)在信息论上是最优的,并表明当测量可高效实现时,自适应性不提供任何优势,其样本复杂度下界分别为:对秩-r态为Ω(r²d/ε²),对阴影层析为Ω(d log M / ε²)。

ABSTRACT

We study the problems of quantum tomography and shadow tomography using measurements performed on individual, identical copies of an unknown $d$-dimensional state. We first revisit a known lower bound due to Haah et al. (2017) on quantum tomography with accuracy $ε$ in trace distance, when the measurements choices are independent of previously observed outcomes (i.e., they are nonadaptive). We give a succinct proof of this result. This leads to stronger lower bounds when the learner uses measurements with a constant number of outcomes. In particular, this rigorously establishes the optimality of the folklore ``Pauli tomography" algorithm in terms of its sample complexity. We also derive novel bounds of $Ω(r^2 d/ε^2)$ and $Ω(r^2 d^2/ε^2)$ for learning rank $r$ states using arbitrary and constant-outcome measurements, respectively, in the nonadaptive case. In addition to the sample complexity, a resource of practical significance for learning quantum states is the number of different measurements used by an algorithm. We extend our lower bounds to the case where the learner performs possibly adaptive measurements from a fixed set of $\exp(O(d))$ measurements. This implies in particular that adaptivity does not give us any advantage using single-copy measurements that are efficiently implementable. We also obtain a similar bound in the case where the goal is to predict the expectation values of a given sequence of observables, a task known as shadow tomography. Finally, in the case of adaptive, single-copy measurements implementable with polynomial-size circuits, we prove that a straightforward strategy based on computing sample means of the given observables is optimal.

研究动机与目标

  • 建立使用单拷贝测量的量子态层析的样本复杂度的信息论下界。
  • 确定当测量可高效实现时,自适应测量策略是否在样本复杂度上优于非自适应策略。
  • 在单拷贝测量约束下分析阴影层析的样本复杂度。
  • 严格建立泡利层析算法在样本复杂度方面的最优性。
  • 量化测量效率(唯一测量设置的数量)与样本复杂度之间的权衡。

提出的方法

  • 使用卡方散度(χ²-divergence)在概率分布之间推导下界,避免依赖于投影到一维子空间的测量算符。
  • 应用卡方散度的测度集中性,将下界扩展至使用固定集合(exp(O(d)))测量设置的自适应测量策略。
  • 使用伯恩斯坦不等式分析经典阴影层析中可观测量样本均值的集中性。
  • 通过在量子态上构造填充集(packing argument)推导出依赖于秩 r 和维度 d 的下界。
  • 通过计算独立同分布测量下的无偏估计量,分析经典阴影框架中期望值的估计。
  • 证明对于可高效实现的、结果数量恒定的测量,计算可观测量的样本均值是最优的,与已知的信息论下界一致。

实验结果

研究问题

  • RQ1学习 d 维量子态至迹距离 ε 所需的最少单拷贝测量次数是多少?
  • RQ2当使用固定且可高效实现的测量设置集合时,自适应性是否在样本复杂度上提供任何优势?
  • RQ3泡利层析算法在样本复杂度方面是否最优?
  • RQ4使用单拷贝测量学习秩-r量子态的样本复杂度的最紧下界是什么?
  • RQ5唯一测量设置的数量如何影响量子态学习中的样本复杂度?

主要发现

  • 论文为非自适应单拷贝层析建立了 Ω(d³/ε²) 的下界,与 KRT17 和 GKKT20 的上界一致。
  • 对于秩-r态,任意单拷贝测量下的样本复杂度下界为 Ω(r²d/ε²),而恒定结果测量下的下界为 Ω(r²d²/ε²)。
  • 当测量集合被限制在 exp(O(d)) 个设置时,自适应测量策略无法改善样本复杂度,表明在此参数范围内自适应性无优势。
  • 使用两结果测量的经典阴影框架在预测 M 个可观测量时达到 O(d log M / ε²) 的样本复杂度,与已知下界相比仅差一个 log²(M) 因子。
  • 泡利层析算法在信息论上是最优的,因其样本复杂度与推导出的下界完全匹配。
  • 对于可由多项式大小电路实现的自适应单拷贝测量,计算可观测量的样本均值是最优策略,不存在更优的策略。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。