Stopping Reliability in Adaptive Krylov-Shadow Quantum Fisher Information Estimation

TL;DR

This paper develops a reliable stopping rule for adaptive Krylov-shadow quantum Fisher information estimation, effectively distinguishing true convergence from false positives caused by bias or sampling errors.

Contribution

It introduces a guarded stopping rule based on empirical interval width and stability, reducing false stops and improving reliability in quantum Fisher information estimation.

Findings

Guarded rule suppresses false success declarations.

False-stop rates range from 0.16 to 0.68 with width-only rule.

Recalibration allows success declarations without false stops.

Abstract

Adaptive quantum Fisher information (QFI) estimation requires a stopping rule that distinguishes accuracy from apparent numerical stability. For Krylov-shadow QFI estimators, finite Krylov order $K$ produces truncation bias, while finite sample budget $M$ produces finite-$M$ sampling-side error. We show that a width-only empirical stopping rule, based on interval width and local Krylov stability, can declare convergence at small $(K,M)$ even when the post hoc error exceeds the requested tolerance; we call this event a \emph{false stop}. The mechanism is a narrow empirical interval centered on a biased low-$K$ estimate. We give a two-component stopping analysis that separates the Krylov and sampling terms, and we implement a guarded rule that permits a success declaration only after minimum thresholds in $K$ and $M$ and a persistence condition are satisfied. On a five-level dephasing benchmark at $n=4$ qubits, the guarded rule suppresses the false success declarations produced by the width-only empirical rule, whose false-stop rates range from $0.16$ to $0.68$ across the tested noise levels. Under the main fixed resource limit, the guarded rule refuses to make success declarations rather than accepting biased low-$K$ estimates; a separate true-relative-tolerance sampling-budget sequence then shows that, after Krylov and sampling recalibration, the same decision principle can make success declarations without observed false stops. These results show that stopping reliability is a distinct design requirement for adaptive QFI estimation: sampling precision at fixed $K$ does not by itself establish that Krylov truncation bias is controlled.