关于量子生成模型中非线性在可模拟性与优化方面的补充研究
A supplemental investigation of non-linearity in quantum generative models with respect to simulatability and optimization
AI总结:
本文针对引入RUS子程序的非线性量子生成模型,研究了其经典可模拟性及训练稳定性,发现该非线性使模型难以经典高效模拟,且在部分数据集上训练稳定性较差。
摘要:
近期的研究表明,通过 repeat-until-success (RUS) 子程序将非线性引入量子电路,在生成建模中具有实用性。作为该工作的后续,我们调查了与量子算法和机器学习社区相关的两个问题:引入这种形式的非线性是否会因延迟测量原理而使学习模型变得经典可模拟?以及引入这种形式的非线性是否会使整个模型的训练变得更加不稳定?针对第一个问题,我们证明 RUS 子程序不允许我们轻易地将该量子模型映射为经典模型,而一个不包含 RUS 子电路但带有电路中途测量的模型,由于量子力学的延迟测量原理,可以被映射为经典贝叶斯网络。这有力地表明,所提出的非线性形式使得该模型在经典上模拟起来效率低下。针对第二个问题,我们在三种不同的概率分布(一个连续分布和两个离散分布)上训练了比以往展示的更大的模型,并比较了多次随机试验中的训练表现。我们发现,尽管该模型在某些试验中表现异常出色,但在某些数据集上不同试验间的方差量化了其相对较差的训练稳定性。
英文摘要:
Recent work has demonstrated the utility of introducing non-linearity through repeat-until-success (RUS) sub-routines into quantum circuits for generative modeling. As a follow-up to this work, we investigate two questions of relevance to the quantum algorithms and machine learning communities: Does introducing this form of non-linearity make the learning model classically simulatable due to the deferred measurement principle? And does introducing this form of non-linearity make the overall model's training more unstable? With respect to the first question, we demonstrate that the RUS sub-routines do not allow us to trivially map this quantum model to a classical one, whereas a model without RUS sub-circuits containing mid-circuit measurements could be mapped to a classical Bayesian network due to the deferred measurement principle of quantum mechanics. This strongly suggests that the proposed form of non-linearity makes the model classically in-efficient to simulate. In the pursuit of the second question, we train larger models than previously shown on three different probability distributions, one continuous and two discrete, and compare the training performance across multiple random trials. We see that while the model is able to perform exceptionally well in some trials, the variance across trials with certain datasets quantifies its relatively poor training stability.
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。