arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.02464quant-phcs.ITcs.LGmath.IT
收藏

机器学习中量子优势的信息论界

Information-theoretic bounds on quantum advantage in machine learning

Caltech(加州理工学院);Johannes Kepler University Linz(约翰内斯·开普勒大学林茨);AWS Center for Quantum Computing(亚马逊云科技量子计算中心)

Hsin-Yuan Huang, Richard Kueng, John Preskill

摘要:

我们研究了经典和量子机器学习(ML)模型在预测物理实验结果方面的性能。实验依赖于输入参数$x$,并涉及(可能未知的)量子过程$\mathcal{E}$的执行。我们的品质因数是达到预期预测性能所需的$\mathcal{E}$运行次数。我们考虑经典ML模型,它在每次运行$\mathcal{E}$后执行测量并记录经典结果,以及量子ML模型,它可以相干地访问$\mathcal{E}$以获取量子数据;然后使用经典或量子数据来预测未来实验的结果。我们证明了对于任何输入分布$\mathcal{D}(x)$,经典ML模型可以通过访问$\mathcal{E}$多次来提供平均准确的预测,与最佳量子ML模型相当。相比之下,为了实现对所有输入的准确预测,我们证明了指数量子优势是可能的。例如,为了预测$n$ -量子比特系统$ρ$中所有泡利观测值的期望值,经典ML模型需要$ρ$的$2^{Ω(n)}$副本,但我们提出了一个仅使用$\mathcal{O}(n)$副本的量子ML模型。我们的研究结果澄清了量子优势的可能性,并强调了经典ML模型解决物理和化学中具有挑战性的量子问题的潜力。

英文摘要:

We study the performance of classical and quantum machine learning (ML) models in predicting outcomes of physical experiments. The experiments depend on an input parameter $x$ and involve execution of a (possibly unknown) quantum process $\mathcal{E}$. Our figure of merit is the number of runs of $\mathcal{E}$ required to achieve a desired prediction performance. We consider classical ML models that perform a measurement and record the classical outcome after each run of $\mathcal{E}$, and quantum ML models that can access $\mathcal{E}$ coherently to acquire quantum data; the classical or quantum data is then used to predict outcomes of future experiments. We prove that for any input distribution $\mathcal{D}(x)$, a classical ML model can provide accurate predictions on average by accessing $\mathcal{E}$ a number of times comparable to the optimal quantum ML model. In contrast, for achieving accurate prediction on all inputs, we prove that exponential quantum advantage is possible. For example, to predict expectations of all Pauli observables in an $n$-qubit system $ρ$, classical ML models require $2^{Ω(n)}$ copies of $ρ$, but we present a quantum ML model using only $\mathcal{O}(n)$ copies. Our results clarify where quantum advantage is possible and highlight the potential for classical ML models to address challenging quantum problems in physics and chemistry.

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。

↑