发表机构
Heritage Institute of Technology（遗产理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究测量了近-term QNLP中VQC在SST-2分类上的模拟器计算成本，发现其训练时间比经典基线慢886至21,127倍，且性能优势不显著，能量消耗近似恒定，表明模拟成本是QNLP实际负担的重要部分。
AI 中文摘要
近-term量子自然语言处理（QNLP）实验通常在经典模拟器上运行，因此模拟器成本是该领域实际计算负担的一部分，但准确率表格并未显示这一点。我们使用PennyLane的状态向量模拟器，在受控的27种配置网格上，对二元SST-2情感分类的变分量子分类器（VQC）测量了这一成本：三种平衡训练集大小（N=200、500、1000），三种量子比特数（4、6、8），以及三种电路深度。每个VQC与在相同PCA降维输入上的逻辑回归进行比较；完整的TF-IDF逻辑回归提供了未压缩的参考。VQC在27次单种子比较中的6次击败了其匹配基线。在另外两个种子的重跑后，这6次中只有1次保持了大于其配对种子间变异性的正平均优势，且在固定验证集上的配对检验并未确立这一优势。VQC训练在实测墙钟时间上比匹配的经典拟合慢886至21,127倍（中位数3,158倍）；从4个量子比特增加到8个量子比特，模拟器时间大约翻倍，且在测试范围内，每步成本可很好地近似为参数数量的线性函数。CodeCarbon的能量和CO2估计是次要的：它们暗示了约41 W的几乎恒定的功率，因此除了运行时间外，它们增加的信息很少，我们并未从中构建能量比。该研究范围狭窄（一个数据集、表示、ansatz、模拟器和CPU环境），是一项可复现的可行性测量，而非对QNLP的一般性结论。
英文摘要
Near-term quantum natural language processing (QNLP) experiments often run on classical simulators, so simulator cost is part of the field's practical compute burden, yet accuracy tables do not show it. We measure that cost for a variational quantum classifier (VQC) on binary SST-2 sentiment classification, using PennyLane's state-vector simulator over a controlled grid of 27 configurations: three balanced training-set sizes (N = 200, 500, 1000), three qubit counts (4, 6, 8), and three circuit depths. Each VQC is compared with logistic regression on the same PCA-reduced input; full TF-IDF logistic regression gives an uncompressed reference. The VQC beats its matched baseline in 6 of 27 single-seed comparisons. After reruns at two further seeds, only 1 of these 6 keeps a positive mean advantage larger than its paired seed-to-seed variability, and paired tests on the fixed validation set do not establish it. VQC training is 886-21,127 times slower in measured wall-clock time than the matched classical fit (median 3,158 times); going from 4 to 8 qubits roughly doubles simulator time, and within the tested range per-step cost is well approximated by a linear function of the parameter count. CodeCarbon energy and CO2 estimates are secondary: they imply an almost constant power of about 41 W, so they add little beyond runtime, and we do not build an energy ratio from them. The study is narrow (one dataset, representation, ansatz, simulator, and CPU environment) and is a reproducible feasibility measurement, not a general verdict on QNLP.
Comments11 pages, 4 figures
