跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2609.14424 · v2

Shot noise can decide capacity comparisons of quantum models

首次提交 2026-09-13 18:47
版本更新 2026-11-16 02:35
雷达观测 2026-11-17 17:12
arXiv ↗PDF ↗

摘要

Shot noise can decide close comparisons of what quantum models appear able to learn. On an IBM processor, the standard estimate of a capacity measure, the effective dimension, placed a 48-qubit model above about 90% of classical networks with as many parameters at 256 shots per circuit. The split-shot estimate from the same data, which removes the bias of the Fisher matrix and needs no noise model, placed it above 12%. A registered run at six parameter points of a 16-qubit model repeated this: the standard estimate placed the three random points above every classical network, the split-shot estimate above 11 to 22%. In simulation the standard estimate reversed the comparison with the classical median at all 100 random points tried. The inflation is the size that shot noise predicts, and a forecast from a pilot run bounds it from above. For squared loss and a linear readout, the error of the standard parameter-shift estimate of a model's Fisher matrix is an exact polynomial in single-shot statistics. Its leading term grows with the effective rank of the matrix, so the shot budget for a stated precision follows from a pilot run; on hardware the observed errors were 0.85 to 1.09 times the predicted ones. The effective dimension can be bracketed from the data but not pinned down at a practical budget. Capacity reports should state their shot count and use the split-shot estimate.

作者备注:44 pages, 9 figures; Supplementary Information as appendices. v2: substantially revised and retitled (v1: "Certification cost of quantum models: measurement correlation, not parameter count"). The cost law of v1 is Theorem 1 here; the light-cone estimator and its hardware tests are in a companion paper

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-16 02:35 · 最新观测版本

Shot noise can decide capacity comparisons of quantum models

Shot noise can decide close comparisons of what quantum models appear able to learn. On an IBM processor, the standard estimate of a capacity measure, the effective dimension, placed a 48-qubit model above about 90% of classical networks with as many parameters at 256 shots per circuit. The split-shot estimate from the same data, which removes the bias of the Fisher matrix and needs no noise model, placed it above 12%. A registered run at six parameter points of a 16-qubit model repeated this: the standard estimate placed the three random points above every classical network, the split-shot estimate above 11 to 22%. In simulation the standard estimate reversed the comparison with the classical median at all 100 random points tried. The inflation is the size that shot noise predicts, and a forecast from a pilot run bounds it from above. For squared loss and a linear readout, the error of the standard parameter-shift estimate of a model's Fisher matrix is an exact polynomial in single-shot statistics. Its leading term grows with the effective rank of the matrix, so the shot budget for a stated precision follows from a pilot run; on hardware the observed errors were 0.85 to 1.09 times the predicted ones. The effective dimension can be bracketed from the data but not pinned down at a practical budget. Capacity reports should state their shot count and use the split-shot estimate.

查看此版本解读 →查看此版本原文 ↗