跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2608.24891 · v2

Measurement-Budget Allocation in Quantum Learning with Finite-Shot Generalization Guarantees

首次提交 2026-06-01 21:43
版本更新 2026-11-19 20:14
雷达观测 2026-11-20 16:53
arXiv ↗PDF ↗

摘要

On near-term quantum hardware, estimating a Born probability requires repeated circuit executions. A quantum learning experiment with a fixed measurement budget BB must therefore decide how many distinct training states nn to use and how many shots SS to spend on each. We study this trade-off for binary quantum classifiers whose measurement operator MM is learned from the training data and evaluated with fresh measurement outcomes. We prove a distribution-free generalization bound for bounded, LL-Lipschitz losses with a sample term of order d/n\sqrt{d/n} and a shot term of order (log⁡n)/S\sqrt{(\log n)/S}; under B=nSB=nS the two terms move in opposite directions. Minimizing a closed-form surrogate of the bound gives the allocation rule n∗=22dB/log⁡(4B/δ)n^* = 2\sqrt{2dB/\log(4B/δ)}, S∗=B/n∗S^* = B/n^*, whose bound value is within 0.1% of the exact numerical minimum on all budgets we evaluate, and a worst-case rate of B−1/4B^{-1/4}. PennyLane simulations with 2- and 4-qubit variational circuits on nine synthetic benchmarks show that the empirical gap stays below the bound in all configurations, although the bound is vacuous at the simulated budgets and becomes non-vacuous only for larger budgets (e.g., B≳5000B \gtrsim 5000 for d=4d=4). For a loss that is concave in the score, the empirical gap is U-shaped under a fixed budget and the measured shot contribution matches its analytical value; for the absolute loss, shot noise is unbiased and no shot-limited regime appears. The rule can be used to plan finite-shot evaluations before an experiment is run.

作者备注:28 pages, 7 figures, 9 tables. v2: revised version; adds a fixed-budget experiment with a concave loss showing the U-shaped trade-off, an analysis of the sources of conservatism, a comparison with the exact numerical minimizer, and corrected logarithmic constants. Code and data: https://github.com/ocatak/quantum-measurement-budget-allocation

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 · 2026-11-19 20:14 · 最新观测版本

Measurement-Budget Allocation in Quantum Learning with Finite-Shot Generalization Guarantees

On near-term quantum hardware, estimating a Born probability requires repeated circuit executions. A quantum learning experiment with a fixed measurement budget BB must therefore decide how many distinct training states nn to use and how many shots SS to spend on each. We study this trade-off for binary quantum classifiers whose measurement operator MM is learned from the training data and evaluated with fresh measurement outcomes. We prove a distribution-free generalization bound for bounded, LL-Lipschitz losses with a sample term of order d/n\sqrt{d/n} and a shot term of order (log⁡n)/S\sqrt{(\log n)/S}; under B=nSB=nS the two terms move in opposite directions. Minimizing a closed-form surrogate of the bound gives the allocation rule n∗=22dB/log⁡(4B/δ)n^* = 2\sqrt{2dB/\log(4B/δ)}, S∗=B/n∗S^* = B/n^*, whose bound value is within 0.1% of the exact numerical minimum on all budgets we evaluate, and a worst-case rate of B−1/4B^{-1/4}. PennyLane simulations with 2- and 4-qubit variational circuits on nine synthetic benchmarks show that the empirical gap stays below the bound in all configurations, although the bound is vacuous at the simulated budgets and becomes non-vacuous only for larger budgets (e.g., B≳5000B \gtrsim 5000 for d=4d=4). For a loss that is concave in the score, the empirical gap is U-shaped under a fixed budget and the measured shot contribution matches its analytical value; for the absolute loss, shot noise is unbiased and no shot-limited regime appears. The rule can be used to plan finite-shot evaluations before an experiment is run.

查看此版本解读 →查看此版本原文 ↗