[论文解读] Do Quantum Circuit Born Machines Generalize?

Kaitlin Gili, Mohamed Hibat-Allah+3 more|arXiv (Cornell University)|Jul 27, 2022

Quantum Computing Algorithms and Architecture被引用 4

一句话总结

本文通过一种新颖的评估框架，研究了量子电路玻恩机（QCBMs）在训练数据之外的泛化性能，超越了简单的记忆化。结果表明，即使仅使用30%的训练数据，QCBMs也能有效泛化到未见过的有效比特串，并从重加权分布中生成更高质量的样本，显示出在优化任务中实现实际量子优势的巨大潜力。

ABSTRACT

In recent proposals of quantum circuit models for generative tasks, the discussion about their performance has been limited to their ability to reproduce a known target distribution. For example, expressive model families such as Quantum Circuit Born Machines (QCBMs) have been almost entirely evaluated on their capability to learn a given target distribution with high accuracy. While this aspect may be ideal for some tasks, it limits the scope of a generative model's assessment to its ability to memorize data rather than generalize. As a result, there has been little understanding of a model's generalization performance and the relation between such capability and the resource requirements, e.g., the circuit depth and the amount of training data. In this work, we leverage upon a recently proposed generalization evaluation framework to begin addressing this knowledge gap. We first investigate the QCBM's learning process of a cardinality-constrained distribution and see an increase in generalization performance while increasing the circuit depth. In the 12-qubit example presented here, we observe that with as few as 30% of the valid data in the training set, the QCBM exhibits the best generalization performance toward generating unseen and valid data. Lastly, we assess the QCBM's ability to generalize not only to valid samples, but to high-quality bitstrings distributed according to an adequately re-weighted distribution. We see that the QCBM is able to effectively learn the reweighted dataset and generate unseen samples with higher quality than those in the training set. To the best of our knowledge, this is the first work in the literature that presents the QCBM's generalization performance as an integral evaluation metric for quantum generative models, and demonstrates the QCBM's ability to generalize to high-quality, desired novel samples.

研究动机与目标

• 为解决量子生成模型（特别是QCBMs）在泛化方面缺乏正式评估的问题。
• 探究QCBMs是否能够学习并泛化到未见过的有效样本，而不仅仅是记忆训练数据。
• 评估电路深度和训练数据规模对泛化性能的影响。
• 探索模型在泛化到有效样本之外，是否也能泛化到高质量、重加权分布的能力。
• 确立泛化作为量子生成模型的关键评估指标，推动评价重点从记忆化转向学习能力。

提出的方法

• 采用一种近期提出的泛化评估框架，以量化QCBM在未见数据上的性能表现。
• 在仅允许固定数量1的比特串（即基数受限分布）上训练QCBMs。
• 通过基于有效性的指标（生成样本中有效样本的比例）和基于质量的指标（在重加权分布上的表现）来评估泛化性能。
• 改变电路深度和训练集规模（从10%到100%的有效数据），以研究其对泛化的影响。
• 使用负对数似然（NLL）和Kullback-Leibler（KL）散度作为辅助指标，评估训练的保真度。
• 在12量子比特的QCBM上开展实验，以分析可扩展性趋势和资源依赖性。

实验结果

研究问题

• RQ1 当在解空间子集上训练时，QCBMs能否泛化到未见过的有效比特串？
• RQ2 增加电路深度如何影响QCBMs的泛化性能？
• RQ3 QCBMs实现强泛化所需的最少训练数据量是多少？
• RQ4 QCBMs能否学习并从与训练数据不同的重加权分布中生成高质量样本？
• RQ5 QCBMs的泛化性能与记忆化性能相比如何？这对实际量子优势有何启示？

主要发现

• 在12量子比特的基数受限数据集中，QCBMs在仅使用30%有效数据的情况下即可实现最优泛化性能。
• 增加电路深度可显著提升泛化性能，表明表达能力的增强有助于实现超越记忆化的学习。
• QCBM成功地从重加权分布中泛化出高质量、未见过的比特串，其生成样本的质量优于训练集中的样本。
• 泛化性能对有效训练样本数量极为敏感，表明数据效率是影响模型性能的关键因素。
• 该模型表现出强劲的有效性导向泛化能力，表明其学习的是底层结构模式，而非简单记忆训练样本。
• 本研究是文献中首次正式将QCBM泛化性能作为核心评估指标，凸显其在约束优化任务中的潜力。