变分量子自然语言推理的SPSA超参数调优
SPSA Hyperparameter Tuning for Variational Quantum Natural Language Inference
查看机构详情
- NPC Worldwide
- Indiana University（印第安纳大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究针对变分量子自然语言推理，在6量子比特QNLI分类器上对SPSA超参数做网格搜索，发现AdamW式SPSA的最优配置性能优于默认配置，但仍逊于参数偏移基准，且Bures预处理会放大SPSA梯度噪声。
中文摘要 AI 辅助
训练变分量子模型时，需在参数偏移梯度与同时扰动随机近似（SPSA）间做选择：前者精确但需要O(P)次前向评估，后者仅用2次采样，但会产生高方差估计，可能在小型监督任务上劣化优化效果。廉价梯度是否可用取决于SPSA扰动尺度、学习率及增益衰减调度的不同选择带来的方差。我们在6量子比特、60参数的QNLI分类器上对这些参数做了大范围网格搜索，将最优配置与参数偏移AdamW及BuresQNG做对比。采用c₀=0.01、η=0.10、γ=0.10的AdamW式SPSA达到了55%±11%的测试准确率，优于默认配置（49%±6%），但仍比参数偏移基准低16-19个百分点，原因是两次采样的SPSA梯度估计方差过大，无法在40个周期内可靠优化60个参数。经典增益SPSA和Bures预处理SPSA表现更差，准确率分别为51%和46%，Bures预处理会放大含噪两次采样SPSA梯度的扰动噪声。
英文摘要
Training variational quantum models requires choosing between parameter-shift gradients, which are exact but cost $O(P)$ forward evaluations, and simultaneous perturbation stochastic approximation (SPSA), which uses only two samples but produces high-variance estimates that can degrade optimisation on small supervised tasks. Whether the cheap gradient is usable depends on the variance that results from different choices of the SPSA perturbation scale, learning rate, and gain-decay schedule. We varied those quantities across a broad grid on a 6-qubit, 60-parameter QNLI classifier and compared the best configurations to parameter-shift AdamW and BuresQNG. AdamW-style SPSA with $c_0=0.01$, $η=0.10$, $γ=0.10$ reached $55\% \pm 11\%$ test accuracy, improving over the default configuration ($49\% \pm 6\%$) but remaining 16-19 percentage points below the parameter-shift baselines because the two-sample SPSA gradient estimate has too much variance for reliable optimisation of 60 parameters in 40 epochs. Classical-gain SPSA and Bures-preconditioned SPSA performed worse, at $51\%$ and $46\%$ respectively. Bures-preconditioning a noisy two-sample SPSA gradient amplifies perturbation noise.
